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

Hämäläinen, Annika; Bosch, L.F.M. ten; Boves, L.W.J.

doi:10.1016/j.specom.2008.07.001

Cited by 7 publications

(2 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The training data contained 396 187 orthographic word tokens (37 h, 20 s of speech). The (standard) triphone training procedure is de scribed in Hämäläinen et al, 2007 for the manual triphones, and in Hämäläinen et al, 2009 for the canonical triphones. For this study, we carried out state tying such that both sets of triphones had about 3400 physically distinct triphones.…”

Section: A Spectral Reduction Scoresmentioning

confidence: 99%

Analysis of acoustic reduction using spectral similarity measures

Hämäläinen

Gubian

Bosch

et al. 2009

The Journal of the Acoustical Society of America

Self Cite

View full text Add to dashboard Cite

Articulatory and acoustic reduction can manifest itself in the temporal and spectral domains. This study introduces a measure of spectral reduction, which is based on the speech decoding techniques commonly used in automatic speech recognizers. Using data for four frequent Dutch affixes from a large corpus of spontaneous face-to-face conversations, it builds on an earlier study examining the effects of lexical frequency on durational reduction in spoken Dutch [Pluymaekers, M. et al. (2005). J. Acoust. Soc. Am. 118, [2561][2562][2563][2564][2565][2566][2567][2568][2569], and compares the proposed measure of spectral reduction with duration as a measure of reduction. The results suggest that the spectral reduction scores capture other aspects of reduction than duration. While duration can-albeit to a moderate degreebe predicted by a number of linguistically motivated variables (such as word frequency, segmental context, and speech rate), the spectral reduction scores cannot. This suggests that the spectral reduction scores capture information that is not directly accounted for by the linguistically motivated variables. The results also show that the spectral reduction scores are able to predict a substantial amount of the variation in duration that the linguistically motivated variables do not account for.

show abstract

Section: A Spectral Reduction Scoresmentioning

confidence: 99%

Analysis of acoustic reduction using spectral similarity measures

Hämäläinen

Gubian

Bosch

et al. 2009

The Journal of the Acoustical Society of America

Self Cite

View full text Add to dashboard Cite

show abstract

“…There, pronunciation variation is usually modeled by adding pronunciation variants to the lexicon [3]- [6]. On the other hand, pronunciation variation can also be represented at the subword level in the acoustic model [4], [7], [8]. Here, a subword is a unit of a hidden Markov model (HMM) composing a word, and it typically corresponds to a phoneme or a triphone in speech recognition.…”

Section: Introductionmentioning

confidence: 99%

Learning Speech Variability in Discriminative Acoustic Model Adaptation

Sato

Oku

Homma

et al. 2010

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYWe present a new discriminative method of acoustic model adaptation that deals with a task-dependent speech variability. We have focused on differences of expressions or speaking styles between tasks and set the objective of this method as improving the recognition accuracy of indistinctly pronounced phrases dependent on a speaking style.The adaptation appends subword models for frequently observable variants of subwords in the task. To find the task-dependent variants, low-confidence words are statistically selected from words with higher frequency in the task's adaptation data by using their word lattices. HMM parameters of subword models dependent on the words are discriminatively trained by using linear transforms with a minimum phoneme error (MPE) criterion. For the MPE training, subword accuracy discriminating between the variants and the originals is also investigated. In speech recognition experiments, the proposed adaptation with the subword variants reduced the word error rate by 12.0% relative in a Japanese conversational broadcast task.

show abstract