Speaker-independent continuous speech dictation

Gauvain, Jean‐Luc; Lamel, Lori; Adda, Gilles; Adda-Decker, Martine

doi:10.1016/0167-6393(94)90038-8

Cited by 57 publications

(21 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It should be noted that the person who classified the phoneme being spoken was not aware of the text of the utterance. The phoneme transcription, which we obtained from the International Computer Science Institute (ICSI) in Berkeley, CA, is based on the LIMSI phonetic alphabet (Gauvain, Lamel, Adda, and Adda-Decker 1994).…”

Section: Datamentioning

confidence: 99%

Stochastic Optimization Methods for Fitting Polyclass and Feed-Forward Neural Network Models

Kooperberg

Stone

1999

Journal of Computational and Graphical Statistics

View full text Add to dashboard Cite

and Stone introduced POLYCLASS, a methodology that uses adaptively selected linear splines and their tensor products to model conditional class probabilities. The authors attempted to develop a methodology that would work well on small and moderate size problems and would scale up to large problems. However, the version of POLYCLASS that was developed for large problems was computationally impractical beyond a certain point. In this article we gain further insight into the fitting of large POLYCLASS models by simultaneously considering the fitting of large feed-forward neural network models with a single hidden layer (NEURALNET). In this combined setting, the stochastic gradient method, as used in the online version of the backpropagation method for fitting neural network models, and a stochastic version of the conjugate gradient method for fitting such models emerge as being computationally attractive. In particular, these stochastic methods are successfully applied to the fitting of POLYCLASS and NEURALNET models in the context of a phoneme recognition problem involving 45 phonemes, 81 features, 150,000 cases in the training sample, up to 1,000 basis functions and 44,000 parameters for POLYCLASS, and up to 800 hidden nodes and about 100,000 parameters for NEURALNET.

show abstract

Section: Datamentioning

confidence: 99%

Stochastic Optimization Methods for Fitting Polyclass and Feed-Forward Neural Network Models

Kooperberg

Stone

1999

Journal of Computational and Graphical Statistics

View full text Add to dashboard Cite

show abstract

“…The real-time, speaker independent, continuous speech recognizer [4] transforms the acoustic signal into the most probable word sequence. The recognition vocabulary contains 1800 words, including about 500 station names.…”

Section: System Overviewmentioning

confidence: 99%

The LIMSI ARISE system for train travel information

Lamel

Rosset

Gauvain

et al. 1999

1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258)

Self Cite

View full text Add to dashboard Cite

In the context of the LE-3 ARISE project we have been developing a dialog system for vocal access to rail travel information. The system provides schedule information for the main French intercity connections, as well as, simulated fares and reservations, reductions and services. Our goal is to obtain high dialog success rates with a very open dialog structure, where the user is free to ask any question or to provide any information at any point in time. In order to improve performance with such an open dialog strategy, we make use of implicit confirmation using the callers wording (when possible), and change to a more constrained dialog level when the dialog is not going well. In addition to own assessment, the prototype system undergoes periodic user evaluations carried out by the our partners at the French Railways.

show abstract

“…It should be noted that the person who determined which phoneme was spoken was not aware of the text of the utterance. The phoneme transcription, which we obtained from the International Computer Science Institute (ICSI) in Berkeley, California, is based on the LIMSI phonetic alphabet (Gauvain et al 1994).…”

Section: Phoneme Recognitionmentioning

confidence: 99%

Polychotomous Regression

Kooperberg

Bose

Stone

1997

Journal of the American Statistical Association

View full text Add to dashboard Cite

An automatic procedure that uses linear splines and their tensor products is proposed for tting a regression model to data involving a polychotomous response variable and one or more predictors. The tted model can be used for multiple classi cation. The automatic tting procedure involves maximum likelihood estimation, stepwise addition, stepwise deletion, and model selection by AIC, cross-validation or an independent test set. A modi ed version of the algorithm has been constructed that is applicable to large data sets, and it is illustrated using a phoneme recognition data set with 250,000 cases, 45 classes and 63 predictors.

show abstract

Speaker-independent continuous speech dictation

Cited by 57 publications

References 9 publications

Stochastic Optimization Methods for Fitting Polyclass and Feed-Forward Neural Network Models

Stochastic Optimization Methods for Fitting Polyclass and Feed-Forward Neural Network Models

The LIMSI ARISE system for train travel information

Polychotomous Regression

Contact Info

Product

Resources

About