A study of speech recognition system robustness to microphone variations: experiments in phonetic classification

Chang, Jane W.; Zue, Victor W.

doi:10.21437/icslp.1994-263

Cited by 6 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…since the latter induce a spreading of spcctnl transitions and make the cumnt analysis output depend on its neighbouring context. Such side effens are critical in continuous subword-unit-based speech recognizers, for which filters may worsen recognition pafonuance [4]. Contextdependent subword units are frequently used in this frameworli since they can model speech coarticulation.…”

Section: Introductionmentioning

confidence: 99%

On parameter filtering in continuous subword-unit-based speech recognition

Pachès-Leal¹,

Nadeu²

1996

4th International Conference on Spoken Language Processing (ICSLP 1996)

View full text Add to dashboard Cite

Simple IIR or FIR f i l m have bem widely used in isolated orword recognition tasks to filter the time sequence of speech spectral parametas, since, despite their simplicity, they significantly improve recognition performance. Those f i l m , when applied to continuous speech recognition, when phonema sized modelling units w used, induce spectral transition spnading and a cross-boundary effect In this work, we show how the use of contextdependent units reduces the side effects of the filters and may result in improved recognition performance. When dynamic parameten are not used. filtering scans to be especially useful, even for clean speech, and when they are, f i l m do well under unmatched training and testing conditions.

show abstract

Section: Introductionmentioning

confidence: 99%

On parameter filtering in continuous subword-unit-based speech recognition

Pachès-Leal¹,

Nadeu²

1996

4th International Conference on Spoken Language Processing (ICSLP 1996)

View full text Add to dashboard Cite

show abstract

Sources of Variability and Distortion in the Communication Process

The International Series in Engineering and Computer Science

View full text Add to dashboard Cite

In this chapter we review the main difficulties encountered in Automatic Speech Recognition (ASR) when the type of communication channel is not known. This is a typical ASR challenge when an arbitrary type of microphone is used, in telephonebased applications or hands-free speech recognition. For promising domains such as computer telephony and cars, the ability to handle these challenges is becoming a requirement more than a desired feature. The main technical problems encountered involve speaker and task variability, the usability of the user interface, the ambient noise which distorts the input speech signals, reverberation and echoes, the use of microphones with different characteristics, the variable quality of the support channels (e.g. telephone channels are noisy and have different characteristics), and the variable distance arid direction to the microphone introduced by hands-free recognition. This chapter presents these sources of variability/distortion along with their influence on ASR.

show abstract

Acoustic Model Adaptation Using First-Order Linear Prediction for Reverberant Speech

Takiguchi

Nishimura

Ariki

2006

IEICE Transactions on Information and Systems

View full text Add to dashboard Cite

This paper describes a hands-free speech recognition technique based on acoustic model adaptation to reverberant speech. In handsfree speech recognition, the recognition accuracy is degraded by reverberation, since each segment of speech is affected by the reflection energy of the preceding segment. To compensate for the reflection signal we introduce a frame-by-frame adaptation method adding the reflection signal to the means of the acoustic model. The reflection signal is approximated by a first-order linear prediction from the observation signal at the preceding frame, and the linear prediction coefficient is estimated with a maximum likelihood method by using the EM algorithm, which maximizes the likelihood of the adaptation data. Its effectiveness is confirmed by word recognition experiments on reverberant speech.

show abstract

A study of speech recognition system robustness to microphone variations: experiments in phonetic classification

Cited by 6 publications

References 0 publications

On parameter filtering in continuous subword-unit-based speech recognition

On parameter filtering in continuous subword-unit-based speech recognition

Sources of Variability and Distortion in the Communication Process

Acoustic Model Adaptation Using First-Order Linear Prediction for Reverberant Speech

Contact Info

Product

Resources

About