Speech segmentation is a subfield of general speech perception and an important subproblem of the technologically focused field of speech recognition, and cannot be adequately solved in isolation. As in most natural language processing problems, one must take into account context, grammar, and semantics, and even so the result is often a probabilistic division (statistically based on likelihood) rather than a categorical one. Though it seems that coarticulation—a phenomenon which may happen between adjacent words just as easily as within a single word—presents the main challenge in speech segmentation across languages, some other problems and strategies employed in solving those problems can be seen in the following sections.
This problem overlaps to some extent with the problem of text segmentation that occurs in some languages which are traditionally written without inter-word spaces, like Chinese and Japanese, compared to writing systems which indicate speech segmentation between words by a word divider, such as the space. However, even for those languages, text segmentation is often much easier than speech segmentation, because the written language usually has little interference between adjacent words, and often contains additional clues not present in speech (such as the use of Chinese characters for word stems in Japanese).
Lexical recognition
In natural languages, the meaning of a complex spoken sentence can be understood by decomposing it into smaller lexical segments (roughly, the words of the language), associating a meaning to each segment, and combining those meanings according to the grammar rules of the language.
Though lexical recognition is not thought to be used by infants in their first year, due to their highly limited vocabularies, it is one of the major processes involved in speech segmentation for adults. Three main models of lexical recognition exist in current research: first, whole-word access, which argues that words have a whole-word representation in the lexicon; second, decomposition, which argues that morphologically complex words are broken down into their morphemes (roots, stems, inflections, etc.) and then interpreted and; third, the view that whole-word and decomposition models are both used, but that the whole-word model provides some computational advantages and is therefore dominant in lexical recognition.[1]
To give an example, in a whole-word model, the word "cats" might be stored and searched for by letter, first "c", then "ca", "cat", and finally "cats". The same word, in a decompositional model, would likely be stored under the root word "cat" and could be searched for after removing the "s" suffix. "Falling", similarly, would be stored as "fall" and suffixed with the "ing" inflection.[2]
Though proponents of the decompositional model recognize that a morpheme-by-morpheme analysis may require significantly more computation, they argue that the unpacking of morphological information is necessary for other processes (such as syntactic structure) which may occur parallel to lexical searches.
As a whole, research into systems of human lexical recognition is limited due to little experimental evidence that fully discriminates between the three main models.[1]
In any case, lexical recognition likely contributes significantly to speech segmentation through the contextual clues it provides, given that it is a heavily probabilistic system—based on the statistical likelihood of certain words or constituents occurring together. For example, one can imagine a situation where a person might say "I bought my dog at a ____ shop" and the missing word's vowel is pronounced as in "net", "sweat", or "pet". While the probability of "netshop" is extremely low, since "netshop" isn't currently a compound or phrase in English, and "sweatshop" also seems contextually improbable, "pet shop" is a good fit because it is a common phrase and is also related to the word "dog".[3]
Moreover, an utterance can have different meanings depending on how it is split into words. A popular example, often quoted in the field, is the phrase "How to wreck a nice beach", which sounds very similar to "How to recognize speech".[4] As this example shows, proper lexical segmentation depends on context and semantics which draws on the whole of human knowledge and experience, and would thus require advanced pattern recognition and artificial intelligence technologies to be implemented on a computer.
Lexical recognition is of particular value in the field of computer speech recognition, since the ability to build and search a network of semantically connected ideas would greatly increase the effectiveness of speech-recognition software. Statistical models can be used to segment and align recorded speech to words or phones. Applications include automatic lip-synch timing for cartoon animation, follow-the-bouncing-ball video sub-titling, and linguistic research. Automatic segmentation and alignment software is commercially available.
Phonotactic cues
For most spoken languages, the boundaries between lexical units are difficult to identify; phonotactics are one answer to this issue. One might expect that the inter-word spaces used by many written languages like English or Spanish would correspond to pauses in their spoken version, but that is true only in very slow speech, when the speaker deliberately inserts those pauses. In normal speech, one typically finds many consecutive words being said with no pauses between them, and often the final sounds of one word blend smoothly or fuse with the initial sounds of the next word.
The notion that speech is produced like writing, as a sequence of distinct vowels and consonants, may be a relic of alphabetic heritage for some language communities. In fact, the way vowels are produced depends on the surrounding consonants just as consonants are affected by surrounding vowels; this is called coarticulation. For example, in the word "kit", the [k] is farther forward than when we say 'caught'. But also, the vowel in "kick" is phonetically different from the vowel in "kit", though we normally do not hear this. In addition, there are language-specific changes which occur in casual speech which makes it quite different from spelling. For example, in English, the phrase "hit you" could often be more appropriately spelled "hitcha".
From a decompositional perspective, in many cases, phonotactics play a part in letting speakers know where to draw word boundaries. In English, the word "strawberry" is perceived by speakers as consisting (phonetically) of two parts: "straw" and "berry". Other interpretations such as "stra" and "wberry" are inhibited by English phonotactics, which does not allow the cluster "wb" word-initially. Other such examples are "day/dream" and "mile/stone" which are unlikely to be interpreted as "da/ydream" or "mil/estone" due to the phonotactic probability or improbability of certain clusters. The sentence "Five women left", which could be phonetically transcribed as [faɪvwɪmɘnlɛft], is marked since neither /vw/ in /faɪvwɪmɘn/ nor /nl/ in /wɪmɘnlɛft/ are allowed as syllable onsets or codas in English phonotactics. These phonotactic cues often allow speakers to easily distinguish the boundaries in words.
Vowel harmony in languages like Finnish can also serve to provide phonotactic cues. While the system does not allow front vowels and back vowels to exist together within one morpheme, compounds allow two morphemes to maintain their own vowel harmony while coexisting in a word. Therefore, in compounds such as "selkä/ongelma" ('back problem') where vowel harmony is distinct between two constituents in a compound, the boundary will be wherever the switch in harmony takes place—between the "ä" and the "ö" in this case.[5] Still, there are instances where phonotactics may not aid in segmentation. Words with unclear clusters or uncontrasted vowel harmony as in "opinto/uudistus" ('student reform') do not offer phonotactic clues as to how they are segmented.[6]
From the perspective of the whole-word model, however, these words are thought be stored as full words, so the constituent parts would not necessarily be relevant to lexical recognition.
In infants and non-natives
Infants are one major focus of research in speech segmentation. Since infants have not yet acquired a lexicon capable of providing extensive contextual clues or probability-based word searches within their first year, as mentioned above, they must often rely primarily upon phonotactic and rhythmic cues (with prosody being the dominant cue), all of which are language-specific. Between 6 and 9 months, infants begin to lose the ability to discriminate between sounds not present in their native language and grow sensitive to the sound structure of their native language, with the word segmentation abilities appearing around 7.5 months.
Though much more research needs to be done on the exact processes that infants use to begin speech segmentation, current and past studies suggest that English-native infants approach stressed syllables as the beginning of words. At 7.5 months, infants appear to be able to segment bisyllabic words with strong-weak stress patterns, though weak-strong stress patterns are often misinterpreted, e.g. interpreting "guiTAR is" as "GUI TARis". It seems that infants also show some complexity in tracking frequency and probability of words, for instance, recognizing that although the syllables "the" and "dog" occur together frequently, "the" also commonly occurs with other syllables, which may lead to the analysis that "dog" is an individual word or concept instead of the interpretation "thedog".[7][8]
Language learners are another set of individuals being researched within speech segmentation. In some ways, learning to segment speech may be more difficult for a second-language learner than for an infant, not only in the lack of familiarity with sound probabilities and restrictions but particularly in the overapplication of the native language's patterns. While some patterns may occur between languages, as in the syllabic segmentation of French and English, they may not work well with languages such as Japanese, which has a mora-based segmentation system. Further, phonotactic restrictions like the boundary-marking cluster /ld/ in German or Dutch are permitted (without necessarily marking boundaries) in English. Even the relationship between stress and vowel length, which may seem intuitive to speakers of English, may not exist in other languages, so second-language learners face an especially great challenge when learning a language and its segmentation cues.[9]
In phonology and linguistics, a phoneme is a set of phones that can distinguish one word from another in a particular language.
Unless otherwise noted, statements in this article refer to Standard Finnish, which is based on the dialect spoken in the former Häme Province in central south Finland. Standard Finnish is used by professional speakers, such as reporters and news presenters on television.
Phonotactics is a branch of phonology that deals with restrictions in a language on the permissible combinations of phonemes. Phonotactics defines permissible syllable structure, consonant clusters and vowel sequences by means of phonotactic constraints.
A root is the core of a word that is irreducible into more meaningful elements. In morphology, a root is a morphologically simple unit which can be left bare or to which a prefix or a suffix can attach. The root word is the primary lexical unit of a word, and of a word family, which carries aspects of semantic content and cannot be reduced into smaller constituents. Content words in nearly all languages contain, and may consist only of, root morphemes. However, sometimes the term "root" is also used to describe the word without its inflectional endings, but with its lexical endings in place. For example, chatters has the inflectional root or lemma chatter, but the lexical root chat. Inflectional roots are often called stems. A root, or a root morpheme, in the stricter sense, may be thought of as a monomorphemic stem.
English phonology is the system of speech sounds used in spoken English. Like many other languages, English has wide variation in pronunciation, both historically and from dialect to dialect. In general, however, the regional dialects of English share a largely similar phonological system. Among other things, most dialects have vowel reduction in unstressed syllables and a complex set of phonological features that distinguish fortis and lenis consonants.
In linguistics, prosody is the study of elements of speech that are not individual phonetic segments but which are properties of syllables and larger units of speech, including linguistic functions such as intonation, stress, and rhythm. Such elements are known as suprasegmentals.
A word is a basic element of language that carries meaning, can be used on its own, and is uninterruptible. Despite the fact that language speakers often have an intuitive grasp of what a word is, there is no consensus among linguists on its definition and numerous attempts to find specific criteria of the concept remain controversial. Different standards have been proposed, depending on the theoretical background and descriptive context; these do not converge on a single definition. Some specific definitions of the term "word" are employed to convey its different meanings at different levels of description, for example based on phonological, grammatical or orthographic basis. Others suggest that the concept is simply a convention used in everyday situations.
In linguistics, a segment is "any discrete unit that can be identified, either physically or auditorily, in the stream of speech". The term is most used in phonetics and phonology to refer to the smallest elements in a language, and this usage can be synonymous with the term phone.
In linguistics, apophony is any alternation within a word that indicates grammatical information.
The Wariʼ language is the sole remaining vibrant language of the Chapacuran language family of the Brazilian–Bolivian border region of the Amazon. It has about 2,700 speakers, also called Wariʼ, who live along tributaries of the Pacaas Novos river in Western Brazil. The word wariʼ means "we!" in the Wariʼ language and is the term given to the language and tribe by its speakers.
This article describes the phonology of the Somali language.
The sonority sequencing principle (SSP) or sonority sequencing constraint is a phonotactic principle that aims to outline the structure of a syllable in terms of sonority.
Text segmentation is the process of dividing written text into meaningful units, such as words, sentences, or topics. The term applies both to mental processes used by humans when reading text, and to artificial processes implemented in computers, which are the subject of natural language processing. The problem is non-trivial, because while some written languages have explicit word boundary markers, such as the word spaces of written English and the distinctive initial, medial and final letter shapes of Arabic, such signals are sometimes ambiguous and not present in all written languages.
Speech perception is the process by which the sounds of language are heard, interpreted, and understood. The study of speech perception is closely linked to the fields of phonology and phonetics in linguistics and cognitive psychology and perception in psychology. Research in speech perception seeks to understand how human listeners recognize speech sounds and use this information to understand spoken language. Speech perception research has applications in building computer systems that can recognize speech, in improving speech recognition for hearing- and language-impaired listeners, and in foreign-language teaching.
Bootstrapping is a term used in language acquisition in the field of linguistics. It refers to the idea that humans are born innately equipped with a mental faculty that forms the basis of language. It is this language faculty that allows children to effortlessly acquire language. As a process, bootstrapping can be divided into different domains, according to whether it involves semantic bootstrapping, syntactic bootstrapping, prosodic bootstrapping, or pragmatic bootstrapping.
Phonological development refers to how children learn to organize sounds into meaning or language (phonology) during their stages of growth.
In linguistics, functional morphemes, also sometimes referred to as functors, are building blocks for language acquisition. A functional morpheme is a morpheme which simply modifies the meaning of a word, rather than supplying the root meaning. Functional morpheme are generally considered a closed class, which means that new functional morphemes cannot normally be created.
Statistical language acquisition, a branch of developmental psycholinguistics, studies the process by which humans develop the ability to perceive, produce, comprehend, and communicate with natural language in all of its aspects through the use of general learning mechanisms operating on statistical patterns in the linguistic input. Statistical learning acquisition claims that infants' language-learning is based on pattern perception rather than an innate biological grammar. Several statistical elements such as frequency of words, frequent frames, phonotactic patterns and other regularities provide information on language structure and meaning for facilitation of language acquisition.
Statistical learning is the ability for humans and other animals to extract statistical regularities from the world around them to learn about the environment. Although statistical learning is now thought to be a generalized learning mechanism, the phenomenon was first identified in human infant language acquisition.
Prosodic bootstrapping in linguistics refers to the hypothesis that learners of a primary language (L1) use prosodic features such as pitch, tempo, rhythm, amplitude, and other auditory aspects from the speech signal as a cue to identify other properties of grammar, such as syntactic structure. Acoustically signaled prosodic units in the stream of speech may provide critical perceptual cues by which infants initially discover syntactic phrases in their language. Although these features by themselves are not enough to help infants learn the entire syntax of their native language, they provide various cues about different grammatical properties of the language, such as identifying the ordering of heads and complements in the language using stress prominence, indicating the location of phrase boundaries, and word boundaries. It is argued that prosody of a language plays an initial role in the acquisition of the first language helping children to uncover the syntax of the language, mainly due to the fact that children are sensitive to prosodic cues at a very young age.
↑ An often-used example in the literature of speech recognition. An early example is N. Rex Dixon, "Some Problems in Automatic Recognition of Continuous Speech and Their Implications for Pattern Recognition" Proceedings of the First International Joint Conference on Pattern Recognition, IEEE, 1973 as quoted in Mark Liberman, "Wrecking a nice beach", Language LogAugust 5, 2014
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.
