Abstract
Recent research on the TIMIT corpus suggests that longer-length acoustic models are more appropriate for pronunciation variation modelling than the context-dependent phones that conventional automatic speech recognisers use. However, the impressive speech recognition results obtained with longer-length models on TIMIT remain to be reproduced on other corpora. To understand the conditions in which longer-length acoustic models result in considerable improvements in recognition performance, we carry out recognition experiments on both TIMIT and the Spoken Dutch Corpus and analyse the differences between the two sets of results. We establish that the details of the procedure used for initialising the longer-length models have a substantial effect on the speech recognition results. When initialised appropriately, longer-length acoustic models that borrow their topology from a sequence of triphones cannot capture the pronunciation variation phenomena that hinder recognition performance the most.
Highlights
Conventional large-vocabulary continuous speech recognisers use context-dependent phone models, such as triphones, to model speech
To estimate the proportion of syllable tokens that were potentially sensitive to large deviations from their canonical representation, we examined the structure of the syllables in the TIMIT database
This paper contrasted recognition results obtained using longer-length acoustic models for Dutch read speech from a library for the blind with recognition results achieved on American English read speech from TIMIT
Summary
Conventional large-vocabulary continuous speech recognisers use context-dependent phone models, such as triphones, to model speech Apart from their capability of modelling (some) contextual effects, the main advantage of triphones is that the fixed number of phonemes in a given language guarantees their robust training when reasonable amounts of training data are available and when state tying methods are used to deal with infrequent triphones. One must assume that speech can be represented as a sequence of discrete phonemes (beads on a string) that can only be substituted, inserted, or deleted to account for pronunciation variation [1]. Given this assumption, it should be possible to account for pronunciation variation at the level of the phonetic transcriptions in the recognition lexicon. We must conclude that a representation of speech in terms of a sequence of discrete symbols is not fully adequate
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: EURASIP Journal on Audio, Speech, and Music Processing
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
