High speed speech recognition using tree-structured probability density function

Watanabe, Takao; Sairyo, Koichi; Takagi, Keizaburo; Iso, Ken-ichi

doi:10.1109/icassp.1995.479658

Cited by 34 publications

(23 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, preprocessing techniques (spectral subtraction for Table 1 Mobile terminal products and chips including speech recognition (see [116,116}121] [102,104,126]. Another aspect that highly interests these manufacturers is the reduction of the computational cost of the ASR algorithm [124,125]. To conclude this section, one can say that ASR can be fully implemented in a terminal if operating on small vocabulary and in isolated or connected words modes.…”

Section: Speech Recognition In Mobile Terminalsmentioning

confidence: 99%

Innovative speech processing for mobile terminals: an annotated bibliography

et al. 2000

View full text Add to dashboard Cite

This paper gives an overview of recent bibliographic references dealing with speech processing in mobile terminals. Its purpose is to point out state of the art issues in the area; thus a fairly large list of references taken from many conferences proceedings and journals is given and commented. General considerations about speech processing in mobile communications are "rstly introduced; then we deal with audio processing for speech enhancement in mobile terminals and with low bit-rate speech coding. Speech recognition is addressed with some accent put on mobile applications. A short overview of implementation aspects of speech processing algorithms in mobile terminals is also given. Finally, open issues and problems are listed.2000 Published by Elsevier Science B.V. All rights reserved. ZusammenfassungDiese Arbeit gibt einen U G berblick auf neue bibliogra"sche Referenzen, die sich mit der Sprachverarbeitung in mobilen Einheiuten beschaK ftigen. Unser Ziel ist es, den Stand der technischen VeroK !entlichungen auf diesem Gebiet zu ermitteln; somit ist eine recht lange Liste von Referenzen aus vielen Konferenzen und Zeitschiften und die zugehoK rigen Kommentare angegeben. Allgemeine U G berlegungen zur Sprachverarbeitung in der Mobilkommunikation werden als erstes angefuK hrt; anschlie{end behandeln wir Verfahren zur Spracheverbesserung in mobilen Systemen basierend auf niedrigen Bitraten. Bei der anschlieend behandelten Spracherkennung wird ein gewisser Schwerpunkt auf mobile Systeme gelegt. Ein kurzer U G berblick zum Implementierungsaspekt der Sparchverarbeitungsverfahren in mobilen EndgeraK ten ist ebenfalls angegeben. Schlielich werden o!ene Themen und Probleme aufgezeigt.2000 Published by Elsevier Science B.V. All rights reserved. Re2 sume2Cet article passe en revue la bibliographie reH cente concernant le traitement de la parole dans les terminaux mobiles. Son objectif est de mettre l'accent sur l'eH tat de l'art dans le domaine; en conseH quence une importante liste de reH feH rences recueillies dans des actes de congre`s et des revues est donneH e et commenteH e. En premier lieu, des consideH rations geH neH rales sur le traitement de la parole dans les communications mobiles sont preH senteH es; puis nous discutons de traitements de rehaussement de la parole dans les terminaux mobiles ainsi que du codage de la parole a`bas deH bits. La reconnaissance vocale est traiteH e avec un accent particulier mis sur les applications mobiles. L'implantation des algorithmes de traitement de la parole dans les terminaux mobiles est aussi brie`vement traiteH e. En"n, certaines questions et proble`mes ouverts sont citeH s.

show abstract

Section: Speech Recognition In Mobile Terminalsmentioning

confidence: 99%

Innovative speech processing for mobile terminals: an annotated bibliography

et al. 2000

View full text Add to dashboard Cite

show abstract

“…Thus, only the likely CGs are selected to impute the candidate clean speech. Existing methods of Gaussian selection can be classified as axis indexing-based methods [37,38] and VQ-based methods [39,40]. The former quickly locates the likely regions based on the observation, then selects the Gaussians in the likely regions [38] or removes the Gaussians in the unlikely regions [37].…”

Section: Selection Of Cgmentioning

confidence: 99%

Multi-candidate missing data imputation for robust speech recognition

Wang

hamme

2012

J AUDIO SPEECH MUSIC PROC.

View full text Add to dashboard Cite

The application of Missing Data Techniques (MDT) to increase the noise robustness of HMM/GMM-based large vocabulary speech recognizers is hampered by a large computational burden. The likelihood evaluations imply solving many constrained least squares (CLSQ) optimization problems. As an alternative, researchers have proposed frontend MDT or have made oversimplifying independence assumptions for the backend acoustic model. In this article, we propose a fast Multi-Candidate (MC) approach that solves the per-Gaussian CLSQ problems approximately by selecting the best from a small set of candidate solutions, which are generated as the MDT solutions on a reduced set of cluster Gaussians. Experiments show that the MC MDT runs equally fast as the uncompensated recognizer while achieving the accuracy of the full backend optimization approach. The experiments also show that exploiting the more accurate acoustic model of the backend does pay off in terms of accuracy when compared to frontend MDT.

show abstract

“…Since the total number of clusters can be much less than the number of states, the problem of choosing the correct information block for sample generation is simplified. A tree structure to group the Gaussian mixtures from clean speech HMMs into clusters can be built with the following distance measure [15]: …”

Section: A Clustering Approach To Obtaining Correct Hmm Informationmentioning

confidence: 99%

A Particle Filter Compensation Approach to Robust Speech Recognition

Mushtaq¹

2012

Modern Speech Recognition Approaches With Case Studies

View full text Add to dashboard Cite

High speed speech recognition using tree-structured probability density function

Cited by 34 publications

References 4 publications

Innovative speech processing for mobile terminals: an annotated bibliography

Innovative speech processing for mobile terminals: an annotated bibliography

Multi-candidate missing data imputation for robust speech recognition

A Particle Filter Compensation Approach to Robust Speech Recognition

Contact Info

Product

Resources

About