FR 4.7 Allgemeine Linguistik Institut für Phonetik, UdS (IPUS)
Overview Modelling the acoustic Signal Hidden-Markov-Modelling
Speech Recognition: Applications
Recognition of an utterance …… on the basis of: Variability in the signal affects both the signal modelling and the way the Lexicon is structured.
Variation in the realisation of words Phonological and phonetic processes can result in different realisations of the same word:
Variation in the realisation of words Sound deletion A sound contained in the „canonical“ form (lexicon form) is not realised.
Variation in the realisation of words Epenthesis A sound NOT contained in the „canonical“ form (lexicon form) is inserted.
Variation in the realisation of words
Variation in the realisation of words Assimilation The (phonological) identity of a sound changes under the influence of the context (segmentally and prosodically conditioned). E.g.,
Variation in the realisation of words The variation arising from phonological processes (deletion, epenthesis and assimilation) can be captured in the lexicon as pronunciation variants.
“Top-down” helps “bottom-up” The lexicon and the language model (which captures the legal word sequences (together they constitute the “top-down” processing) help to resolve the ambiguities which arise during the signal processing stage (“bottom-up” processing), since only those sound sequences which correspond to a possible sequence in the lexicon entries, can be recognised by an ASR system.
Variation in the realisation of words Ambiguities in the Signal arise also from the phonetic variation which results from the coarticulation between (neighbouring) sounds, so:
Variation in the realisation of words a sound a single acoustic pattern Example: /h/ can look very different in different contexts. /h/ could be described as „a voiceless“ realisation of the context vowels (in particular of the following vowel). See: (Spectrograms “ihi”, “aha”, “uhu”: different realisations of /h/)
Variation in the realisation of words
Variation in the realisation of words Example: The articulatory gesture for the vowel // overlaps with the gesture for the neighbouring fricatives. (Spectrogram “Dezimalsystem”: no clear separation of the sounds)
Variation in the realisation of words
Variation in the realisation of words Articulatory Transitions Example: At the boundary of the vowel, the realisation depends strongly on the articulation of the neighbouring sound. (Spectrogram “aba”, “ada”, “aga”: Variation in the vowel //)
Variation in the realisation of words
Variation in the realisation of words
Markov-Modelling
You start in state S (no emission) and go from there with a probability of p = 1 to state 1. There you take a black ball from the container.
MMs: A simple example Then you either go on to the 2nd state (p = 0.4) and take a red ball from the container, or you stay by the 1st container and take another black ball. And so on, until you land in state E and have collected a number of coloured balls.
Hidden Markov Modelling
Hidden Markov Modelling
HMMs: A simple example You start in state S (no emission) and go from there to state 1 with a probability of p = 1.
HMMs: A simple example Then you either go on to the 2nd state (p = 0.4) and take a ball from the container, or you stay by the 1st container and take another ball. And so on, until you land in state E and have collected a number of coloured balls.
HMMs: Hidden states
HMMs: Transitions
HMMs: Emissions
HMMs: more complexe models
HMMs: Paucity of data?
HMMs: Speech recognition
HMMs: Lexicon
HMMs: Lexicon
HMMs: Language model
HMMs: Language model
Literature: Van Alphen, P. und D. van Bergem (1989). „Markov models and their application in speech recognition,“ Proceedings Institute of Phonetic Sciences, University of Amsterdam 13, 1-26. Holmes, J. (1988). Speech Synthesis and Recognition (Kap. 8). Wokingham (Berks.): Van Nostrand Reinhold, 129-152. Holmes, J. (1991). Spracherkennung und Sprachsynthese (Kap. 8). München: Oldenburg.
Literature: Cox, S. (1988). „Hidden Markov models for automatic speech recognition: theory and application,“ Br. Telecom techn. Journal 6(2), 105-115. Lee, K.-F. (1989). „Hidden Markov modelling: past, present, future,“ Proc. Eurospeech 1989, vol. 1, 148-155.
Do'stlaringiz bilan baham: |