Multimodal interaction

Last updated

Multimodal interaction provides the user with multiple modes of interacting with a system. A multimodal interface provides several distinct tools for input and output of data.

Contents

Multimodal human-computer interaction involves natural communication with virtual and physical environments. It facilitates free and natural communication between users and automated systems, allowing flexible input (speech, handwriting, gestures) and output (speech synthesis, graphics). Multimodal fusion combines inputs from different modalities, addressing ambiguities.

Two major groups of multimodal interfaces focus on alternate input methods and combined input/output. Multiple input modalities enhance usability, benefiting users with impairments. Mobile devices often employ XHTML+Voice for input. Multimodal biometric systems use multiple biometrics to overcome limitations. Multimodal sentiment analysis involves analyzing text, audio, and visual data for sentiment classification. GPT-4, a multimodal language model, integrates various modalities for improved language understanding. Multimodal output systems present information through visual and auditory cues, using touch and olfaction. Multimodal fusion integrates information from different modalities, employing recognition-based, decision-based, and hybrid multi-level fusion.

Ambiguities in multimodal input are addressed through prevention, a-posterior resolution, and approximation resolution methods.

Introduction

Multimodal human-computer interaction refers to the "interaction with the virtual and physical environment through natural modes of communication", [1] This implies that multimodal interaction enables a more free and natural communication, interfacing users with automated systems in both input and output. [2] Specifically, multimodal systems can offer a flexible, efficient and usable environment allowing users to interact through input modalities, such as speech, handwriting, hand gesture and gaze, and to receive information by the system through output modalities, such as speech synthesis, smart graphics and other modalities, opportunely combined. Then a multimodal system has to recognize the inputs from the different modalities combining them according to temporal and contextual constraints [3] in order to allow their interpretation. This process is known as multimodal fusion, and it is the object of several research works from the nineties to now. [4] [5] [6] [7] [8] [9] [10] [11] The fused inputs are interpreted by the system. Naturalness and flexibility can produce more than one interpretation for each different modality (channel) and for their simultaneous use, and they consequently can produce multimodal ambiguity [12] generally due to imprecision, noises or other similar factors. For solving ambiguities, several methods have been proposed. [13] [14] [15] [16] [17] [18] Finally the system returns to the user outputs through the various modal channels (disaggregated) arranged according to a consistent feedback (fission). [19] The pervasive use of mobile devices, sensors and web technologies can offer adequate computational resources to manage the complexity implied by the multimodal interaction. "Using cloud for involving shared computational resources in managing the complexity of multimodal interaction represents an opportunity. In fact, cloud computing allows delivering shared scalable, configurable computing resources that can be dynamically and automatically provisioned and released". [20]

Multimodal input

Two major groups of multimodal interfaces have merged, one concerned in alternate input methods and the other in combined input/output. The first group of interfaces combined various user input modes beyond the traditional keyboard and mouse input/output, such as speech, pen, touch, manual gestures, [21] gaze and head and body movements. [22] The most common such interface combines a visual modality (e.g. a display, keyboard, and mouse) with a voice modality (speech recognition for input, speech synthesis and recorded audio for output). However other modalities, such as pen-based input or haptic input/output may be used. Multimodal user interfaces are a research area in human-computer interaction (HCI).

The advantage of multiple input modalities is increased usability: the weaknesses of one modality are offset by the strengths of another. On a mobile device with a small visual interface and keypad, a word may be quite difficult to type but very easy to say (e.g. Poughkeepsie). Consider how you would access and search through digital media catalogs from these same devices or set top boxes. And in one real-world example, patient information in an operating room environment is accessed verbally by members of the surgical team to maintain an antiseptic environment, and presented in near realtime aurally and visually to maximize comprehension.

Multimodal input user interfaces have implications for accessibility. [23] A well-designed multimodal application can be used by people with a wide variety of impairments. Visually impaired users rely on the voice modality with some keypad input. Hearing-impaired users rely on the visual modality with some speech input. Other users will be "situationally impaired" (e.g. wearing gloves in a very noisy environment, driving, or needing to enter a credit card number in a public place) and will simply use the appropriate modalities as desired. On the other hand, a multimodal application that requires users to be able to operate all modalities is very poorly designed.

The most common form of input multimodality in the market makes use of the XHTML+Voice (aka X+V) Web markup language, an open specification developed by IBM, Motorola, and Opera Software. X+V is currently under consideration by the W3C and combines several W3C Recommendations including XHTML for visual markup, VoiceXML for voice markup, and XML Events, a standard for integrating XML languages. Multimodal browsers supporting X+V include IBM WebSphere Everyplace Multimodal Environment, Opera for Embedded Linux and Windows, and ACCESS Systems NetFront for Windows Mobile. To develop multimodal applications, software developers may use a software development kit, such as IBM WebSphere Multimodal Toolkit, based on the open source Eclipse framework, which includes an X+V debugger, editor, and simulator.[ citation needed ]

Multimodal biometrics

This section is an excerpt from Biometrics § Multimodal biometric system.[ edit ]

Multimodal biometric systems use multiple sensors or biometrics to overcome the limitations of unimodal biometric systems. [24] For instance iris recognition systems can be compromised by aging irises [25] and electronic fingerprint recognition can be worsened by worn-out or cut fingerprints. While unimodal biometric systems are limited by the integrity of their identifier, it is unlikely that several unimodal systems will suffer from identical limitations. Multimodal biometric systems can obtain sets of information from the same marker (i.e., multiple images of an iris, or scans of the same finger) or information from different biometrics (requiring fingerprint scans and, using voice recognition, a spoken passcode). [26] [27]

Multimodal biometric systems can fuse these unimodal systems sequentially, simultaneously, a combination thereof, or in series, which refer to sequential, parallel, hierarchical and serial integration modes, respectively. Fusion of the biometrics information can occur at different stages of a recognition system. In case of feature level fusion, the data itself or the features extracted from multiple biometrics are fused. Matching-score level fusion consolidates the scores generated by multiple classifiers pertaining to different modalities. Finally, in case of decision level fusion the final results of multiple classifiers are combined via techniques such as majority voting. Feature level fusion is believed to be more effective than the other levels of fusion because the feature set contains richer information about the input biometric data than the matching score or the output decision of a classifier. Therefore, fusion at the feature level is expected to provide better recognition results. [24]

Spoof attacks consist in submitting fake biometric traits to biometric systems, and are a major threat that can curtail their security. Multi-modal biometric systems are commonly believed to be intrinsically more robust to spoof attacks, but recent studies [28] have shown that they can be evaded by spoofing even a single biometric trait.

Multimodal sentiment analysis

This section is an excerpt from Multimodal sentiment analysis.[ edit ]

Multimodal sentiment analysis is a technology for traditional text-based sentiment analysis, which includes modalities such as audio and visual data. [29] It can be bimodal, which includes different combinations of two modalities, or trimodal, which incorporates three modalities. [30] With the extensive amount of social media data available online in different forms such as videos and images, the conventional text-based sentiment analysis has evolved into more complex models of multimodal sentiment analysis, [31] which can be applied in the development of virtual assistants, [32] analysis of YouTube movie reviews, [33] analysis of news videos, [34] and emotion recognition (sometimes known as emotion detection) such as depression monitoring, [35] among others.

Similar to the traditional sentiment analysis, one of the most basic task in multimodal sentiment analysis is sentiment classification, which classifies different sentiments into categories such as positive, negative, or neutral. [36] The complexity of analyzing text, audio, and visual features to perform such a task requires the application of different fusion techniques, such as feature-level, decision-level, and hybrid fusion. [31] The performance of these fusion techniques and the classification algorithms applied, are influenced by the type of textual, audio, and visual features employed in the analysis. [37]

Multimodal language models

This section is an excerpt from GPT-4.[ edit ]
Part of a series on
Machine learning
and data mining
Paradigms
Problems
Clustering
Dimensionality reduction
Structured prediction
Anomaly detection
Artificial neural network
Reinforcement learning
Learning with humans
Model diagnostics
Mathematical foundations
Machine-learning venues
Related articles

Generative Pre-trained Transformer 4 (GPT-4) is a multimodal large language model created by OpenAI, and the fourth in its series of GPT foundation models. [38] It was launched on March 14, 2023, [38] and made publicly available via the paid chatbot product ChatGPT Plus, via OpenAI's API, and via the free chatbot Microsoft Copilot. [39] As a transformer-based model, GPT-4 uses a paradigm where pre-training using both public data and "data licensed from third-party providers" is used to predict the next token. After this step, the model was then fine-tuned with reinforcement learning feedback from humans and AI for human alignment and policy compliance. [40] : 2 

Observers reported that the iteration of ChatGPT using GPT-4 was an improvement on the previous iteration based on GPT-3.5, with the caveat that GPT-4 retains some of the problems with earlier revisions. [41] GPT-4, equipped with vision capabilities (GPT-4V), [42] is capable of taking images as input on ChatGPT. [43] OpenAI has declined to reveal various technical details and statistics about GPT-4, such as the precise size of the model. [44]

Multimodal output

The second group of multimodal systems presents users with multimedia displays and multimodal output, primarily in the form of visual and auditory cues. Interface designers have also started to make use of other modalities, such as touch and olfaction. Proposed benefits of multimodal output system include synergy and redundancy. The information that is presented via several modalities is merged and refers to various aspects of the same process. The use of several modalities for processing exactly the same information provides an increased bandwidth of information transfer . [45] [46] [47] Currently, multimodal output is used mainly for improving the mapping between communication medium and content and to support attention management in data-rich environment where operators face considerable visual attention demands. [48]

An important step in multimodal interface design is the creation of natural mappings between modalities and the information and tasks. The auditory channel differs from vision in several aspects. It is omnidirectional, transient and is always reserved. [48] Speech output, one form of auditory information, received considerable attention. Several guidelines have been developed for the use of speech. Michaelis and Wiggins (1982) suggested that speech output should be used for simple short messages that will not be referred to later. It was also recommended that speech should be generated in time and require an immediate response.

The sense of touch was first utilized as a medium for communication in the late 1950s. [49] It is not only a promising but also a unique communication channel. In contrast to vision and hearing, the two traditional senses employed in HCI, the sense of touch is proximal: it senses objects that are in contact with the body, and it is bidirectional in that it supports both perception and acting on the environment.

Examples of auditory feedback include auditory icons in computer operating systems indicating users' actions (e.g. deleting a file, open a folder, error), speech output for presenting navigational guidance in vehicles, and speech output for warning pilots on modern airplane cockpits. Examples of tactile signals include vibrations of the turn-signal lever to warn drivers of a car in their blind spot, the vibration of auto seat as a warning to drivers, and the stick shaker on modern aircraft alerting pilots to an impending stall. [48]

Invisible interface spaces became available using sensor technology. Infrared, ultrasound and cameras are all now commonly used. [50] Transparency of interfacing with content is enhanced providing an immediate and direct link via meaningful mapping is in place, thus the user has direct and immediate feedback to input and content response becomes interface affordance (Gibson 1979).

Multimodal fusion

The process of integrating information from various input modalities and combining them into a complete command is referred as multimodal fusion. [5] In literature, three main approaches to the fusion process have been proposed, according to the main architectural levels (recognition and decision) at which the fusion of the input signals can be performed: recognition-based, [9] [10] [51] decision-based, [7] [8] [11] [52] [53] [54] [55] and hybrid multi-level fusion. [4] [6] [56] [57] [58] [59] [60] [61]

The recognition-based fusion (also known as early fusion) consists in merging the outcomes of each modal recognizer by using integration mechanisms, such as, for example, statistical integration techniques, agent theory, hidden Markov models, artificial neural networks, etc. Examples of recognition-based fusion strategies are action frame, [51] input vectors [9] and slots. [10]

The decision-based fusion (also known as late fusion) merges the semantic information that are extracted by using specific dialogue-driven fusion procedures to yield the complete interpretation. Examples of decision-based fusion strategies are typed feature structures, [52] [57] melting pots, [54] [55] semantic frames, [7] [11] and time-stamped lattices. [8]

The potential applications for multimodal fusion include learning environments, consumer relations, security/surveillance, computer animation, etc. Individually, modes are easily defined, but difficulty arises in having technology consider them a combined fusion. [62] It is difficult for the algorithms to factor in dimensionality; there exist variables outside of current computation abilities. For example, semantic meaning: two sentences could have the same lexical meaning but different emotional information. [62]

In the hybrid multi-level fusion, the integration of input modalities is distributed among the recognition and decision levels. The hybrid multi-level fusion includes the following three methodologies: finite-state transducers, [57] multimodal grammars [6] [56] [58] [59] [60] [61] [63] and dialogue moves. [64]

Ambiguity

User's actions or commands produce multimodal inputs (multimodal message [3] ), which have to be interpreted by the system. The multimodal message is the medium that enables communication between users and multimodal systems. It is obtained by merging information that are conveyed via several modalities by considering the different types of cooperation between several modalities, [65] the time relationships [66] among the involved modalities and the relationships between chunks of information connected with these modalities. [67]

The natural mapping between the multimodal input, which is provided by several interaction modalities (visual and auditory channel and sense of touch), and information and tasks imply to manage the typical problems of human-human communication, such as ambiguity. An ambiguity arises when more than one interpretation of input is possible. A multimodal ambiguity [12] arises both, if an element, which is provided by one modality, has more than one interpretation (i.e. ambiguities are propagated at the multimodal level), and/or if elements, connected with each modality, are univocally interpreted, but information referred to different modalities are incoherent at the syntactic or the semantic level (i.e. a multimodal sentence having different meanings or different syntactic structure).

In "The Management of Ambiguities", [14] the methods for solving ambiguities and for providing the correct interpretation of the user's input are organized in three main classes: prevention, a-posterior resolution and approximation resolution methods. [13] [15]

Prevention methods impose users to follow predefined interaction behaviour according to a set of transitions between different allowed states of the interaction process. Example of prevention methods are: procedural method, [68] reduction of the expressive power of the language grammar, [69] improvement of the expressive power of the language grammar. [70]

The a-posterior resolution of ambiguities uses mediation approach. [16] Examples of mediation techniques are: repetition, e.g. repetition by modality, [16] granularity of repair [71] and undo, [17] and choice. [18]

The approximation resolution methods do not require any user involvement in the disambiguation process. They can all require the use of some theories, such as fuzzy logic, Markov random field, Bayesian networks and hidden Markov models. [13] [15]

See also

Related Research Articles

<span class="mw-page-title-main">User interface</span> Means by which a user interacts with and controls a machine

In the industrial design field of human–computer interaction, a user interface (UI) is the space where interactions between humans and machines occur. The goal of this interaction is to allow effective operation and control of the machine from the human end, while the machine simultaneously feeds back information that aids the operators' decision-making process. Examples of this broad concept of user interfaces include the interactive aspects of computer operating systems, hand tools, heavy machinery operator controls and process controls. The design considerations applicable when creating user interfaces are related to, or involve such disciplines as, ergonomics and psychology.

Affective computing is the study and development of systems and devices that can recognize, interpret, process, and simulate human affects. It is an interdisciplinary field spanning computer science, psychology, and cognitive science. While some core ideas in the field may be traced as far back as to early philosophical inquiries into emotion, the more modern branch of computer science originated with Rosalind Picard's 1995 paper on affective computing and her book Affective Computing published by MIT Press. One of the motivations for the research is the ability to give machines emotional intelligence, including to simulate empathy. The machine should interpret the emotional state of humans and adapt its behavior to them, giving an appropriate response to those emotions.

Biometrics are body measurements and calculations related to human characteristics. Biometric authentication is used in computer science as a form of identification and access control. It is also used to identify individuals in groups that are under surveillance.

<span class="mw-page-title-main">Gesture recognition</span> Topic in computer science and language technology

Gesture recognition is an area of research and development in computer science and language technology concerned with the recognition and interpretation of human gestures. A subdiscipline of computer vision, it employs mathematical algorithms to interpret gestures.

<span class="mw-page-title-main">Sensor fusion</span> Combining of sensor data from disparate sources

Sensor fusion is the process of combining sensor data or data derived from disparate sources such that the resulting information has less uncertainty than would be possible when these sources were used individually. For instance, one could potentially obtain a more accurate location estimate of an indoor object by combining multiple data sources such as video cameras and WiFi localization signals. The term uncertainty reduction in this case can mean more accurate, more complete, or more dependable, or refer to the result of an emerging view, such as stereoscopic vision.

Human-centered computing (HCC) studies the design, development, and deployment of mixed-initiative human-computer systems. It is emerged from the convergence of multiple disciplines that are concerned both with understanding human beings and with the design of computational artifacts. Human-centered computing is closely related to human-computer interaction and information science. Human-centered computing is usually concerned with systems and practices of technology use while human-computer interaction is more focused on ergonomics and the usability of computing artifacts and information science is focused on practices surrounding the collection, manipulation, and use of information.

In the context of human–computer interaction, a modality is the classification of a single independent channel of input/output between a computer and a human. Such channels may differ based on sensory nature, or other significant differences in processing . A system is designated unimodal if it has only one modality implemented, and multimodal if it has more than one. When multiple modalities are available for some tasks or aspects of a task, the system is said to have overlapping modalities. If multiple modalities are available for a task, the system is said to have redundant modalities. Multiple modalities can be used in combination to provide complementary methods that may be redundant but convey information more effectively. Modalities can be generally defined in two forms: computer-human and human-computer modalities.

A voice-user interface (VUI) enables spoken human interaction with computers, using speech recognition to understand spoken commands and answer questions, and typically text to speech to play a reply. A voice command device is a device controlled with a voice user interface.

<span class="mw-page-title-main">Dialogue system</span>

A dialogue system, or conversational agent (CA), is a computer system intended to converse with a human. Dialogue systems employed one or more of text, speech, graphics, haptics, gestures, and other modes for communication on both the input and output channel.

SCXML stands for State Chart XML: State Machine Notation for Control Abstraction. It is an XML-based markup language that provides a generic state-machine-based execution environment based on Harel statecharts.

The Multimodal Interaction Activity is an initiative from W3C aiming to provide means to support Multimodal interaction scenarios on the Web.

<span class="mw-page-title-main">Interaction technique</span>

An interaction technique, user interface technique or input technique is a combination of hardware and software elements that provides a way for computer users to accomplish a single task. For example, one can go back to the previously visited page on a Web browser by either clicking a button, pressing a key, performing a mouse gesture or uttering a speech command. It is a widely used term in human-computer interaction. In particular, the term "new interaction technique" is frequently used to introduce a novel user interface design idea.

In computing, 3D interaction is a form of human-machine interaction where users are able to move and perform interaction in 3D space. Both human and machine process information where the physical position of elements in the 3D space is relevant.

<span class="mw-page-title-main">Human–computer interaction</span> Academic discipline studying the relationship between computer systems and their users

Human–computer interaction (HCI) is research in the design and the use of computer technology, which focuses on the interfaces between people (users) and computers. HCI researchers observe the ways humans interact with computers and design technologies that allow humans to interact with computers in novel ways. A device that allows interaction between human being and a computer is known as a "Human-computer Interface (HCI)".

Multimodal Architecture and Interfaces is an open standard developed by the World Wide Web Consortium since 2005. It was published as a Recommendation of the W3C on October 25, 2012. The document is a technical report specifying a multimodal system architecture and its generic interfaces to facilitate integration and multimodal interaction management in a computer system. It has been developed by the W3C's Multimodal Interaction Working Group.

Multimodal learning, in the context of machine learning, is a type of deep learning using a combination of various modalities of data, often arising in real-world applications. An example of multi-modal data is data that combines text with imaging data consisting of pixel intensities and annotation tags. As these modalities have fundamentally different statistical properties, combining them is non-trivial, which is why specialized modelling strategies and algorithms are required. The model is then trained to able to understand and work with multiple forms of data.

Emotion recognition is the process of identifying human emotion. People vary widely in their accuracy at recognizing the emotions of others. Use of technology to help people with emotion recognition is a relatively nascent research area. Generally, the technology works best if it uses multiple modalities in context. To date, the most work has been conducted on automating the recognition of facial expressions from video, spoken expressions from audio, written expressions from text, and physiology as measured by wearables.

Joëlle Coutaz is a French computer scientist, specializing in human-computer interaction (HCI). Her career includes research in the fields of operating systems and HCI, as well as being a professor at the University of Grenoble. Coutaz is considered a pioneer in HCI in France, and in 2007, she was awarded membership to SIGCHI. She was also involved in organizing CHI conferences and was a member on the editorial board of ACM Transactions on Computer-Human Interaction.

Multimodal sentiment analysis is a technology for traditional text-based sentiment analysis, which includes modalities such as audio and visual data. It can be bimodal, which includes different combinations of two modalities, or trimodal, which incorporates three modalities. With the extensive amount of social media data available online in different forms such as videos and images, the conventional text-based sentiment analysis has evolved into more complex models of multimodal sentiment analysis, which can be applied in the development of virtual assistants, analysis of YouTube movie reviews, analysis of news videos, and emotion recognition such as depression monitoring, among others.

<span class="mw-page-title-main">Shumin Zhai</span> Human–computer interaction research scientist

Shumin Zhai is a Chinese-born American Canadian Human–computer interaction (HCI) research scientist and inventor. He is known for his research specifically on input devices and interaction methods, swipe-gesture-based touchscreen keyboards, eye-tracking interfaces, and models of human performance in human-computer interaction. His studies have contributed to both foundational models and understandings of HCI and practical user interface designs and flagship products. He previously worked at IBM where he invented the ShapeWriter text entry method for smartphones, which is a predecessor to the modern Swype keyboard. Dr. Zhai's publications have won the ACM UIST Lasting Impact Award and the IEEE Computer Society Best Paper Award, among others, and he is most known for his research specifically on input devices and interaction methods, swipe-gesture-based touchscreen keyboards, eye-tracking interfaces, and models of human performance in human-computer interaction. Dr. Zhai is currently a Principal Scientist at Google where he leads and directs research, design, and development of human-device input methods and haptics systems.

References

  1. ↑ Bourguet, M.L. (2003). "Designing and Prototyping Multimodal Commands". Proceedings of Human-Computer Interaction (INTERACT'03), pp. 717-720.
  2. ↑ Stivers, T., Sidnell, J. Introduction: Multimodal interaction. Semiotica, 156(1/4), pp. 1-20. 2005.
  3. 1 2 Caschera M. C., Ferri F., Grifoni P. (2007). "Multimodal interaction systems: information and time features". International Journal of Web and Grid Services (IJWGS), Vol. 3 - Issue 1, pp 82-99.
  4. 1 2 D'Ulizia, A., Ferri, F. and Grifoni, P. (2010). "Generating Multimodal Grammars for Multimodal Dialogue Processing". IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans, Vol 40, no 6, pp. 1130 – 1145.
  5. 1 2 D'Ulizia , A. (2009). "Exploring Multimodal Input Fusion Strategies". In: Grifoni P (ed) Handbook of Research on Multimodal Human Computer Interaction and Pervasive Services: Evolutionary Techniques for Improving Accessibility. IGI Publishing, pp. 34-57.
  6. 1 2 3 Sun, Y., Shi, Y., Chen, F. and Chung , V.(2007). "An Efficient Multimodal Language Processor for Parallel Input Strings in Multimodal Input Fusion," in Proc. of the international Conference on Semantic Computing, pp. 389-396.
  7. 1 2 3 Russ, G., Sallans, B., Hareter, H. (2005). "Semantic Based Information Fusion in a Multimodal Interface". International Conference on Human-Computer Interaction (HCI'05), Las Vegas, Nevada, USA, 20–23 June, pp 94-100.
  8. 1 2 3 Corradini, A., Mehta M., Bernsen, N.O., Martin, J.-C. (2003). "Multimodal Input Fusion in Human-Computer Interaction on the Example of the on-going NICE Project". In Proceedings of the NATO-ASI conference on Data Fusion for Situation Monitoring, Incident Detection, Alert and Response Management, Yerevan, Armenia.
  9. 1 2 3 Pavlovic, V.I., Berry, G.A., Huang, T.S. (1997). "Integration of audio/visual information for use in human-computer intelligent interaction". Proceedings of the 1997 International Conference on Image Processing (ICIP '97), Volume 1, pp. 121-124.
  10. 1 2 3 Andre, M., Popescu, V.G., Shaikh, A., Medl, A., Marsic, I., Kulikowski, C., Flanagan J.L. (1998). "Integration of Speech and Gesture for Multimodal Human-Computer Interaction". In Second International Conference on Cooperative Multimodal Communication. 28–30 January, Tilburg, The Netherlands.
  11. 1 2 3 Vo, M.T., Wood, C. (1996). "Building an application framework for speech and pen input integration in multimodal learning interfaces". In Proceedings of the Acoustics, Speech, and Signal Processing (ICASSP'96), May 7–10, IEEE Computer Society, Volume 06, pp. 3545-3548.
  12. 1 2 Caschera, M.C. , Ferri, F. , Grifoni, P. (2013). "From Modal to Multimodal Ambiguities: a Classification Approach", Journal of Next Generation Information Technology (JNIT), Vol. 4, No. 5, pp. 87 -109.
  13. 1 2 3 Caschera, M.C. , Ferri, F. , Grifoni, P. (2013). InteSe: An Integrated Model for Resolving Ambiguities in Multimodal Sentences". IEEE Transactions on Systems, Man, and Cybernetics: Systems, Volume: 43, Issue: 4, pp. 911 - 931.18. Spilker, J., Klarner, M., Görz, G. (2000). "Processing Self Corrections in a speech to speech system". COLING 2000. pp. 1116-1120.
  14. 1 2 Caschera M.C., Ferri F., Grifoni P., (2007). "The Management of ambiguities". In Visual Languages for Interactive Computing: Definitions and Formalizations. IGI Publishing. pp.129-140.
  15. 1 2 3 J. Chai, P. Hong, and M. X. Zhou, (2004 )."A probabilistic approach to reference resolution in multimodal user interface" in Proc. 9th Int. Conf. Intell. User Interf., Madeira, Portugal, Jan. 2004, pp. 70–77.
  16. 1 2 3 Dey, A. K. Mankoff , J., (2005). "Designing mediation for context-aware applications". ACM Trans. Comput.-Hum. Interact. 12(1), pp. 53-80.
  17. 1 2 Spilker, J., Klarner, M., Görz, G. (2000). "Processing Self Corrections in a speech to speech system". COLING 2000. pp. 1116-1120.
  18. 1 2 Mankoff, J., Hudson, S.E., Abowd, G.D. (2000). "Providing integrated toolkit-level support for ambiguity in recognition-based interfaces". Proceedings of ACM CHI'00 Conference on Human Factors in Computing Systems. pp. 368 – 375.
  19. ↑ Grifoni P (2009) Multimodal fission. In: Multimodal human computer interaction and pervasive services. IGI Global, pp 103–120
  20. ↑ Patrizia Grifoni, Fernando Ferri, Maria Chiara Caschera, Arianna D'Ulizia, Mauro Mazzei, "MIS: Multimodal Interaction Services in a cloud perspective", JNIT: Journal of Next Generation Information Technology, Vol. 5, No. 4, pp. 01 ~ 10, 2014
  21. ↑ Kettebekov, Sanshzar, and Rajeev Sharma (2001). "Toward Natural Gesture/Speech Control of a Large Display." ProceedingsEHCI '01 Proceedings of the 8th IFIP International Conference on Engineering for Human-Computer Interaction Pages 221-234
  22. ↑ Marius Vassiliou, V. Sundareswaran, S. Chen, R. Behringer, C. Tam, M. Chan, P. Bangayan, and J. McGee (2000), "Integrated Multimodal Human-Computer Interface and Augmented Reality for Interactive Display Applications," in Darrel G. Hopper (ed.) Cockpit Displays VII: Displays for Defense Applications (Proc. SPIE . 4022), 106-115. ISBN   0-8194-3648-8
  23. ↑ Vitense, H.S.; Jacko, J.A.; Emery, V.K. (2002). "Multimodal feedback: establishing a performance baseline for improved access by individuals with visual impairments". ACM Conf. on Assistive Technologies.
  24. 1 2 Haghighat, Mohammad; Abdel-Mottaleb, Mohamed; Alhalabi, Wadee (2016). "Discriminant Correlation Analysis: Real-Time Feature Level Fusion for Multimodal Biometric Recognition". IEEE Transactions on Information Forensics and Security. 11 (9): 1984–1996. doi:10.1109/TIFS.2016.2569061. S2CID   15624506.
  25. ↑ "Questions Raised About Iris Recognition Systems". Science Daily. 12 July 2012. Archived from the original on 22 October 2012.
  26. ↑ Saylor, Michael (2012). The Mobile Wave: How Mobile Intelligence Will Change Everything. Perseus Books/Vanguard Press. p. 99. ISBN   9780306822988.
  27. ↑ Bill Flook (3 October 2013). "This is the 'biometric war' Michael Saylor was talking about". Washington Business Journal. Archived from the original on 7 October 2013.
  28. ↑ Zahid Akhtar, "Security of Multimodal Biometric Systems against Spoof Attacks" (PDF). Archived 2 April 2015 at the Wayback Machine . Department of Electrical and Electronic Engineering, University of Cagliari. Cagliari, Italy, 6 March 2012.
  29. ↑ Soleymani, Mohammad; Garcia, David; Jou, Brendan; Schuller, Björn; Chang, Shih-Fu; Pantic, Maja (September 2017). "A survey of multimodal sentiment analysis". Image and Vision Computing. 65: 3–14. doi:10.1016/j.imavis.2017.08.003. S2CID   19491070.
  30. ↑ Karray, Fakhreddine; Milad, Alemzadeh; Saleh, Jamil Abou; Mo Nours, Arab (2008). "Human-Computer Interaction: Overview on State of the Art" (PDF). International Journal on Smart Sensing and Intelligent Systems. 1: 137–159. doi: 10.21307/ijssis-2017-283 .
  31. 1 2 Poria, Soujanya; Cambria, Erik; Bajpai, Rajiv; Hussain, Amir (September 2017). "A review of affective computing: From unimodal analysis to multimodal fusion". Information Fusion. 37: 98–125. doi:10.1016/j.inffus.2017.02.003. hdl: 1893/25490 . S2CID   205433041.
  32. ↑ "Google AI to make phone calls for you". BBC News. 8 May 2018. Retrieved 12 June 2018.
  33. ↑ Wollmer, Martin; Weninger, Felix; Knaup, Tobias; Schuller, Bjorn; Sun, Congkai; Sagae, Kenji; Morency, Louis-Philippe (May 2013). "YouTube Movie Reviews: Sentiment Analysis in an Audio-Visual Context" (PDF). IEEE Intelligent Systems. 28 (3): 46–53. doi:10.1109/MIS.2013.34. S2CID   12789201.
  34. ↑ Pereira, Moisés H. R.; Pádua, Flávio L. C.; Pereira, Adriano C. M.; Benevenuto, Fabrício; Dalip, Daniel H. (9 April 2016). "Fusing Audio, Textual and Visual Features for Sentiment Analysis of News Videos". arXiv: 1604.02612 [cs.CL].
  35. ↑ Zucco, Chiara; Calabrese, Barbara; Cannataro, Mario (November 2017). "Sentiment analysis and affective computing for depression monitoring". 2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). IEEE. pp. 1988–1995. doi:10.1109/bibm.2017.8217966. ISBN   978-1-5090-3050-7. S2CID   24408937.
  36. ↑ Pang, Bo; Lee, Lillian (2008). Opinion mining and sentiment analysis. Hanover, MA: Now Publishers. ISBN   978-1601981509.
  37. ↑ Sun, Shiliang; Luo, Chen; Chen, Junyu (July 2017). "A review of natural language processing techniques for opinion mining systems". Information Fusion. 36: 10–25. doi:10.1016/j.inffus.2016.10.004.
  38. 1 2 Edwards, Benj (March 14, 2023). "OpenAI's GPT-4 exhibits "human-level performance" on professional benchmarks". Ars Technica . Archived from the original on March 14, 2023. Retrieved March 15, 2023.
  39. ↑ Wiggers, Kyle (2023-07-06). "OpenAI makes GPT-4 generally available". TechCrunch. Archived from the original on August 16, 2023. Retrieved 2023-08-16.
  40. ↑ OpenAI (2023). "GPT-4 Technical Report". arXiv: 2303.08774 [cs.CL].
  41. ↑ Belfield, Haydn (March 25, 2023). "If your AI model is going to sell, it has to be safe". Vox . Archived from the original on March 28, 2023. Retrieved March 30, 2023.
  42. ↑ "GPT-4V(ision) system card". openai.com. Retrieved 2024-02-05.
  43. ↑ Roose, Kevin (2023-09-28). "The New ChatGPT Can 'See' and 'Talk.' Here's What It's Like". The New York Times. Archived from the original on October 31, 2023. Retrieved 2023-10-30.
  44. ↑ Vincent, James (March 15, 2023). "OpenAI co-founder on company's past approach to openly sharing research: "We were wrong"". The Verge . Archived from the original on March 17, 2023. Retrieved March 18, 2023.
  45. ↑ Oviatt, S. (2002), "Multimodal interfaces", in Jacko, J.; Sears, A (eds.), The Human-Computer Interaction Handbook (PDF), Lawrence Erlbaum
  46. ↑ Bauckhage, C.; Fritsch, J.; Rohlfing, K.J.; Wachsmuth, S.; Sagerer, G. (2002). "Evaluating integrated speech-and image understanding". Int. Conf. on Multimodal Interfaces. doi:10.1109/ICMI.2002.1166961.
  47. ↑ Ismail, N.A.; O'Brien, E.A. (2008). "Enabling Multimodal Interaction in Web-Based Personal Digital Photo Browsing" (PDF). Int. Conf. on Computer and Communication Engineering. Archived from the original (PDF) on 2011-07-18. Retrieved 2010-03-03.
  48. 1 2 3 Sarter, N.B. (2006). "Multimodal information presentation: Design guidance and research challenges". International Journal of Industrial Ergonomics. 36 (5): 439–445. doi:10.1016/j.ergon.2006.01.007.
  49. ↑ Geldar, F.A. (1957). "Adventures in tactile literacy". American Psychologist. 12 (3): 115–124. doi:10.1037/h0040416.
  50. ↑ Brooks, A.; Petersson, E. (2007). "SoundScapes: non-formal learning potentials from interactive VEs". SIGGRAPH. doi:10.1145/1282040.1282059.
  51. 1 2 Vo, M.T. (1998). "A framework and Toolkit for the Construction of Multimodal Learning Interfaces", PhD. Thesis, Carnegie Mellon University, Pittsburgh, USA.
  52. 1 2 Cohen, P.R.; Johnston, M.; McGee, D.; Oviatt, S.L.; Pittman, J.; Smith, I.A.; Chen, L.; Clow, J. (1997). "Quickset: Multimodal interaction for distributed applications", ACM Multimedia, pp. 31-40.
  53. ↑ Johnston, M. (1998). "Unification-based Multimodal Parsing". Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics (COLING-ACL '98), August 10–14, Université de Montréal, Montreal, Quebec, Canada. pp. 624-630.
  54. 1 2 Nigay, L.; Coutaz, J. (1995). "A generic platform for addressing the multimodal challenge". Proceedings of the Conference on Human Factors in Computing Systems, ACM Press.
  55. 1 2 Bouchet, J.; Nigay, L.; Ganille, T. (2004). "Icare software components for rapidly developing multimodal interfaces". ICMI '04: Proceedings of the 6th international conference on Multimodal interfaces (New York, NY, USA), ACM, pp. 251-258.
  56. 1 2 D'Ulizia, A.; Ferri, F.; Grifoni P. (2007). "A Hybrid Grammar-Based Approach to Multimodal Languages Specification", OTM 2007 Workshop Proceedings, 25–30 November 2007, Vilamoura, Portugal, Springer-Verlag, Lecture Notes in Computer Science 4805, pp. 367-376.
  57. 1 2 3 Johnston, M.; Bangalore, S. (2000). "Finite-state Multimodal Parsing and Understanding", In Proceedings of the International Conference on Computational Linguistics, Saarbruecken, Germany.
  58. 1 2 Sun, Y.; Chen, F.; Shi, Y.D.; Chung, V. (2006). "A novel method for multi-sensory data fusion in multimodal human computer interaction". In Proceedings of the 20th conference of the computer-human interaction special interest group (CHISIG) of Australia on Computer-human interaction: design: activities, artefacts and environments, Sydney, Australia, pp. 401-404
  59. 1 2 Shimazu, H.; Takashima, Y. (1995). "Multimodal Definite Clause Grammar," Systems and Computers in Japan, vol. 26, no 3, pp. 93-102.
  60. 1 2 Johnston, M.; Bangalore, S. (2005). "Finite-state multimodal integration and understanding," Nat. Lang. Eng, Vol. 11, no. 2, pp. 159-187.
  61. 1 2 Reitter, D.; Panttaja, E. M.; Cummins, F. (2004). "UI on the fly: Generating a multimodal user interface," in Proc. of HLT-NAACL-2004, Boston, Massachusetts, USA.
  62. 1 2 Guan, Ling. "Methods and Techniques for MultiModal Information Fusion" (PDF). Circuits & Systems Society.
  63. ↑ D'Ulizia, A.; Ferri, F.; Grifoni P. (2011). "A Learning Algorithm for Multimodal Grammar Inference", IEEE Transactions on Systems, Man, and Cybernetics - Part B: Cybernetics, Vol. 41 (6), pp. 1495 - 1510.
  64. ↑ Pérez, G.; Amores, G.; Manchón, P. (2005). "Two strategies for multimodal fusion". In Proceedings of Multimodal Interaction for the Visualization and Exploration of Scientific Data, Trento, Italy, 26–32.
  65. ↑ Martin, J.C. (1997). "Toward intelligent cooperation between modalities: the example of a system enabling multimodal interaction with a map", Proceedings of International Joint Conference on Artificial Intelligence (IJCAI'97) Workshop on 'Intelligent Multimodal Systems', Nagoya, Japan
  66. ↑ Allen, J.F.; Ferguson, G. (1994). "Actions and events in interval temporal logic", Journal of Logic and Computation, Vol. 4, No. 5, pp.531–579
  67. ↑ Bellik, Y. (2001). "Technical requirements for a successful multimodal interaction", International Workshop on Information Presentation and Natural Multimodal Dialogue, Verona, Italy, 14–15 December
  68. ↑ Lee, Y.C.; Chin, F. (1995). "An Iconic Query Language for Topological Relationship in GIS". International Journal of geographical Information Systems 9(1). pp. 25-46
  69. ↑ Calcinelli, D.; Mainguenaud, M. (1994). "Cigales, a visual language for geographic information system: the user interface". Journal of Visual Languages and Computing 5(2). pp. 113-132
  70. ↑ Ferri, F.; Rafanelli, M. (2005). "GeoPQL: A Geographical Pictorial Query Language That Resolves Ambiguities in Query Interpretation". J. Data Semantics III. pp.50-80
  71. ↑ Suhm, B., Myers, B. and Waibel, A. (1999). "Model-based and empirical evaluation of multimodal interactive error correction". In Proc. Of CHI'99, May, 1999, pp. 584-591
This page is based on this Wikipedia article
Text is available under the CC BY-SA 4.0 license; additional terms may apply.
Images, videos and audio are available under their respective licenses.