MacSpeech

Last updated
MacSpeech, Inc.
IndustrySpeech recognition and voice dictation software
FoundedMarch 7, 1997 (1997-03-07)
SuccessorNuance Communications, Inc.
Headquarters
Salem, New Hampshire
Products
  • iListen
  • MacSpeech Dictate
  • MacSpeech Scribe

MacSpeech, Inc. was a New Hampshire-based technology company that produced software-based speech recognition and voice dictation solutions for the Apple ecosystem. The company's products included iListen, MacSpeech Dictate, MacSpeech Dictate Medical, MacSpeech Dictate Legal, MacSpeech Dictate International, and MacSpeech Scribe. On February 12, 2010, Nuance Communications, Inc. acquired MacSpeech. [1]

Contents

History

The first commercial voice dictation product for Mac OS X was IBM's ViaVoice, but ScanSoft, the company that had exclusive global distribution rights to ViaVoice, merged with Nuance and stopped developing ViaVoice for Macintosh. (The first dictation software for Mac OS 9 was Articulate System's PowerSecretary.) [2] Seeing a continued need for a Mac-based speech-to-text solution, MacSpeech was founded in 1996 by Andrew Taylor, a former employee of Articulate Systems [3] experienced with software-based speech recognition technologies.

iListen

MacSpeech's first product, iListen, was developed in partnership with Philips Speech Processing using its "FreeSpeech 2000" speech engine. First released in 2000, by 2006 iListen was the only third-party software product that allowed voice-to-text input on the newer MacIntosh models requiring OSX. Its competitors at the time were Apple's own speech recognition software (built into Mac OS X); Dragon Naturally Speaking for PC by Nuance, running under a Windows virtualization software solution such as Parallels Desktop for Mac or VMware Fusion; and the discontinued program ViaVoice by Nuance/IBM.

MacSpeech Dictate

In January 2008, iListen was discontinued, and replaced by "MacSpeech Dictate" (released February 15, 2008). The firm abandoned the Philips speech engine in favor of the speech-recognition engine Nuance used in its Dragon NaturallySpeaking product for PC. MacSpeech Dictate was a winner of the MacWorld 2008 Best of Show award. [4] In 2009, the firm released several editions of its products for the MacIntosh, including MacSpeech Dictate Medical, MacSpeech Dictate Legal and MacSpeech Dictate International.

MacSpeech Dictate ran as a Mac-native application. It used the Dragon speech recognition engine (v9 or v10), licensed from Nuance Communications. This is the same technology that powers speech recognition in Dragon NaturallySpeaking for the PC, although across platforms there are significant differences in features, functionality and integration. One major difference with MacSpeech Dictate was that it did not allow training by typing misrecognized words as Dragon NaturallySpeaking products do on Windows. Another notable difference was the lack of a transcription feature for recorded voice dictation, as found in NaturallySpeaking. MacSpeech released a separate product, MacSpeech Scribe, to handle this.

MacSpeech Dictate Medical, a version with specialized vocabularies for doctors and dentists, was released in June 2009. [5] MacSpeech Dictate Legal, with specialized vocabulary for lawyers, was released in July 2009. [6] MacSpeech Dictate International, with support for speech recognition in English, French, German and Italian, was released in September 2009. [7] Localized versions of MacSpeech Dictate are available in German, French and Italian. [8] It has never been available in Spanish.

The original release used Dragon's v9 speech recognition engine. Version 1.5 was released in May 2009, and gained Microsoft Word integration, vocabulary editing features, and the Dragon v10 engine. Version 2.0 was released in September 2010, after the Dragon acquisition, and was renamed Dragon Dictate for Mac. Version 2 had the Dragon v11 engine, new voice commands for text editing, and a text-to-speech proofreading feature.

MacSpeech Dictate 1.0 was reviewed by David Pogue of The New York Times , who said it filled a "big [hole] in the Macintosh landscape", but criticized it as inferior to Dragon NaturallySpeaking 9.0 for Windows. [9]

MacSpeech Scribe

MacSpeech Scribe is speech recognition software for Mac OS X designed specifically for transcription of recorded voice dictation. It runs on Mac OS X 10.6 Snow Leopard. The software transcribes dictation recorded by an individual speaker. Typically the speaker will have recorded their dictation using a digital recording device such as a handheld digital recorder, mobile smartphone (e.g. iPhone), or desktop or laptop computer with a suitable microphone. The program supports the audio file formats aif, .aiff, .wav, .mp4, .m4a, and .m4v.

Acquisition by Nuance

On February 12, 2010, MacSpeech, Inc. was acquired by Nuance Communications, Inc., and MacSpeech's products were incorporated into Nuance's Dragon NaturalSpeaking product line. [1]

See also

Related Research Articles

Speech recognition is an interdisciplinary subfield of computer science and computational linguistics that develops methodologies and technologies that enable the recognition and translation of spoken language into text by computers with the main benefit of searchability. It is also known as automatic speech recognition (ASR), computer speech recognition or speech to text (STT). It incorporates knowledge and research in the computer science, linguistics and computer engineering fields. The reverse process is speech synthesis.

<span class="mw-page-title-main">Dictaphone</span> American producer of dictation machines

Dictaphone was an American company founded by Alexander Graham Bell that produced dictation machines. It is now a division of Nuance Communications, based in Burlington, Massachusetts.

IBM ViaVoice was a range of language-specific continuous speech recognition software products offered by IBM. The current version is designed primarily for use in embedded devices. The latest stable version of IBM Via Voice was 9.0 and was able to transfer text directly into Word.

SpeechWorks was a company founded in Boston in 1994 by speech recognition pioneer Mike Phillips and Bill O'Farrell. The Boston-based company developed and supported speech-related computer software. Originally known as Applied Language Technologies, SpeechWorks went public in 2000 and tripled its value. ScanSoft acquired Nuance in 2003, and changed its name to Nuance Communications.

PlainTalk is the collective name for several speech synthesis (MacinTalk) and speech recognition technologies developed by Apple Inc. In 1990, Apple invested a lot of work and money in speech recognition technology, hiring many researchers in the field. The result was "PlainTalk", released with the AV models in the Macintosh Quadra series from 1993. It was made a standard system component in System 7.1.2, and has since been shipped on all PowerPC and some 68k Macintoshes.

<span class="mw-page-title-main">Dragon NaturallySpeaking</span> Speech recognition software package

Dragon NaturallySpeaking is a speech recognition software package developed by Dragon Systems of Newton, Massachusetts, which was acquired in turn by Lernout & Hauspie Speech Products, Nuance Communications, and Microsoft. It runs on Windows personal computers. Version 15, which supports 32-bit and 64-bit editions of Windows 7, 8 and 10, was released in August 2016.

A voice-user interface (VUI) makes spoken human interaction with computers possible, 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.

DragonDictate, Dragon Dictate, or Dragon for Mac is proprietary speech recognition software. The older program, DragonDictate, was originally developed by Dragon Systems for Microsoft Windows. It has now been replaced by Dragon NaturallySpeaking for Windows, and has since been acquired by Nuance Communications. Dragon Dictate for Mac 2.0 is supported only on Mac OS X 10.6. Nuance's other products for Mac include MacSpeech Scribe.

iListen, developed by MacSpeech, is a speech recognition program for the Apple Macintosh. In 2006, iListen was the only third-party software that allowed inputting text using one's voice that works on newer Macintosh models. Its competitors were Apple's own speech recognition software ; Dragon Naturally Speaking by Nuance, running under Windows virtualization software such as Parallels Desktop for Mac or VMware Fusion; and the discontinued speech recognition program ViaVoice by Nuance/IBM.

<i>Pillars of Garendall</i> 2001 video game

Pillars of Garendall is a role-playing video game that was built by Beenox Studios and Ambrosia Software. It was built using the Coldstone game engine, which was also a joint Beenox/Ambrosia project. The game was released in 2001 for Mac OS Classic, Microsoft Windows and Mac OS X.

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

Jott was a web-based voice-to-text transcription service which allowed its users to call a toll-free telephone number and speak for up to 30 seconds. The speech was then transcribed to text using a combination of computerized speech recognition software and human transcribers who worked in a "sterile environment which also includes medical dictation." The message could be sent back to oneself, turned into a reminder, sent to a contact or group, or sent to a third-party "Jott link" such as LiveJournal.

As of the early 2000s, several speech recognition (SR) software packages exist for Linux. Some of them are free and open-source software and others are proprietary software. Speech recognition usually refers to software that attempts to distinguish thousands of words in a human language. Voice control may refer to software used for communicating operational commands to a computer.

<span class="mw-page-title-main">Windows Speech Recognition</span> Speech recognition software

Windows Speech Recognition (WSR) is speech recognition developed by Microsoft for Windows Vista that enables voice commands to control the desktop user interface; dictate text in electronic documents and email; navigate websites; perform keyboard shortcuts; and to operate the mouse cursor. It supports custom macros to perform additional or supplementary tasks.

Swype was a virtual keyboard for touchscreen smartphones and tablets originally developed by Swype Inc., founded in 2002, where the user enters words by sliding a finger or stylus from the first letter of a word to its last letter, lifting only between words. It uses error-correction algorithms and a language model to guess the intended word. It also includes a predictive text system, handwriting and speech recognition support. Swype was first commercially available on the Samsung Omnia II running Windows Mobile, and was originally pre-loaded on specific devices.

The Voice Navigator was the first voice recognition device for command and control of a graphical user interface. The system was developed by Articulate System, Inc. originally designed for the Apple Macintosh Plus and released in 1989. Subsequent versions were created for Microsoft Windows. Articulate System, Inc. was acquired by Dragon Systems in 1998.

MacSpeech Scribe is speech recognition software for Mac OS X designed specifically for transcription of recorded voice dictation. It runs on Mac OS X 10.6 Snow Leopard. The software transcribes dictation recorded by an individual speaker. Typically the speaker will record their dictation using a digital recording device such as a handheld digital recorder, mobile smartphone, or desktop or laptop computer with a suitable microphone. MacSpeech Scribe supports specific audio file formats for recorded dictation: .aif, .aiff, .wav, .mp4, .m4a, and .m4v.

Dragon Dictation started as speech recognition application for Apple's iOS platforms, including iPhone, iPod Touch and iPad. The app provided automatic speech-to-text capabilities. It was developed by Nuance Communications, and released in December 2009 as a free app. It is now commonly found licensed in vehicle infotainment systems and healthcare equipment.

<span class="mw-page-title-main">Speech Processing Solutions</span> Manufacturer of speech processing devices

Speech Processing Solutions is an international electronics company headquartered in Vienna, Austria. The company designs, develops, manufactures and markets speech processing devices, such as those used in digital dictation and speech recognition. Speech Processing Solutions was formed on 1 July 2012. Philips Speech Processing was part of the Philips Consumer Lifestyle sector. Speech Processing Solutions is now an official licensee of the Philips brand. The company has subsidiaries in the US, Canada, Australia, the United Kingdom, Belgium, France and Germany, and employs around 170 people worldwide.

Michael Phillips is the CEO and co-founder of Sense Labs and a pioneer in machine learning, including mobile speech recognition and text-to-speech technology.

References

  1. 1 2 "Nuance Acquires MacSpeech, Extending Dragon NaturallySpeaking Family to the Mac" . Retrieved 2017-02-04.
  2. ↑ "TidBITS Apple Ups the AMTE". tidbits.com. Retrieved 16 July 2016.
  3. ↑ "MacSpeech - MacSpeech People". 2008-11-13. Archived from the original on 2008-11-13. Retrieved 2017-02-04.
  4. ↑ "Macworld Expo Best of Show award winners". macworld.com. Retrieved 16 July 2016.
  5. ↑ "MacSpeech, Inc. Releases MacSpeech Dictate Medical". 2009-06-18. Archived from the original on 2011-01-01. Retrieved 2010-06-25.
  6. ↑ "MacSpeech, Inc. Ships MacSpeech Dictate Legal". 2009-07-01. Archived from the original on 2011-01-01. Retrieved 2010-06-25.
  7. ↑ "MacSpeech, Inc. Ships MacSpeech Dictate International". 2009-09-15. Archived from the original on 2010-01-08. Retrieved 2010-06-25.
  8. ↑ "MacSpeech Dictate Localized In German, French and Italian". 2009-09-15. Archived from the original on 2010-01-24. Retrieved 2010-06-25.
  9. ↑ Pogue, David (2008-01-24). "New Tools to Bolster Mac's World". The New York Times. ISSN   0362-4331 . Retrieved 2023-02-04.
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.