On the Utility of Syllable-Based Acoustic Models for Pronunciation Variation Modelling

Abstract

Recent research on the TIMIT corpus suggests th at longer-length acoustic models are more appropriate for pronunciation variation modelling than the context-dependent phones th at conventional autom atic speech recognisers use. However, the impressive speech recognition results obtained with longer-length models on TIMIT rem ain to be reproduced on other corpora. To understand the conditions in which longer-length acoustic models result in considerable im provem ents in recognition performance, we carry out recognition experiments on both TIMIT and the Spoken D utch C orpus and analyse the differences between the two sets of results. We establish th at the details o f the procedure used for initialising the longer-length models have a substantial effect on the speech recognition results. W hen initialised appropriately, longer-length acoustic models that borrow their topology from a sequence of triphones cannot capture the pronunciation variation phenom ena th at hinder recognition perform ance the most.

Modelling pronunciation variation with single-path and multi-path syllable models: Issues to consider

“…To alleviate the problems of the 'beads on a string' representation of speech, several authors propose modelling the spectral and temporal variation in speech 'implicitly' by using longerlength linguistic units as the basic building blocks of speech (Ganapathiraju et al, 2001;Hämäläinen et al, 2007a;Jones et al, 1997;Jouvet and Messina, 2004;Plannerer and Ruske, 1992;. For various reasons, most of these authors (Ganapathiraju et al, 2001;Hämäläinen et al, 2007a;Jones et al, 1997;Jouvet and Messina, 2004; suggest using syllable-length models.…”

“…For various reasons, most of these authors (Ganapathiraju et al, 2001;Hämäläinen et al, 2007a;Jones et al, 1997;Jouvet and Messina, 2004; suggest using syllable-length models. First, using syllables allows for a relatively compact representation of speech, while maintaining a manageable level of recogniser complexity.…”

“…First, syllable models with a sufficient amount of training data are used in combination with triphones (Ganapathiraju et al, 2001;Hämäläinen et al, 2007a;Jouvet and Messina, 2004;. In other words, triphones are backed off to when a given syllable does not occur frequently enough for reliable model parameter estimation.…”

“…Second, to ensure that a relatively small amount of training data is sufficient, the syllable models are cleverly initialised (Hämäläinen et al, 2007a;Jouvet and Messina, 2004;. , for instance, suggest initialising the single-path syllable models with the parameters of the biphones and triphones underlying the canonical transcription of the syllables (see Figure 1).…”

Discourse oriented summarization

“…Other projects of IMIX were responsible for question answering (van den Bosch et al, 2004;Tjong Kim Sang et al, 2005;Bouma et al, 2007), dialog and action management (op den Akker et al, 2005), speech synthesis (Marsi, 2004), and speech recognition (Hämäläinen et al, 2007). Work in this thesis contributed to the answer presentation module of IMIX.…”