Live search for mobile:Web services by voice on the cellphone

Acero, Alex; Bernstein, N.; Chambers, R.; Ju, Yun-Cheng; Li, X.; Odell, JJ; Nguyen, Patrick; Scholz, O.; Zweig, Geoffrey

doi:10.1109/icassp.2008.4518845

Cited by 55 publications

(29 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CD-DNN-HMMs combine the representational power of deep neural networks and the sequential modeling ability of context-dependent hidden Markov models (HMMs). In this paper, we illustrate the key ingredients of the model, describe the procedure to learn the CD-DNN-HMMs' parameters, analyze how various important design choices affect the recognition performance, and demonstrate that CD-DNN-HMMs can significantly outperform strong discriminatively-trained context-dependent Gaussian mixture model hidden Markov model (CD-GMM-HMM) baselines on the challenging business search dataset of [36], collected under actual usage conditions. To our best knowledge, this is the first time DNN-HMMs, which are formerly only used for phone recognition, are successfully applied to large vocabulary speech recognition (LVSR) problems.…”

Section: Introductionmentioning

confidence: 99%

“…In section III, we describe the basic ideas, the key properties, and the training and decoding strategies of our CD-DNN-HMMs. In section IV we analyze experimental results on a 65K+ vocabulary business search dataset collected from the Bing mobile voice search application (formerly known as Live Search for mobile [36], [60]) under real usage scenarios. Section V offers conclusions and directions for future work.…”

Section: B Introduction To the Dnn-hmm Approachmentioning

confidence: 99%

See 1 more Smart Citation

Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition

Dahl

Deng

et al. 2012

IEEE Trans. Audio Speech Lang. Process.

Self Cite

2,631

1,175

View full text Add to dashboard Cite

Abstract-We propose a novel context-dependent (CD) model for large vocabulary speech recognition (LVSR) that leverages recent advances in using deep belief networks for phone recognition. We describe a pre-trained deep neural network hidden Markov model (DNN-HMM) hybrid architecture that trains the DNN to produce a distribution over senones (tied triphone states) as its output. The deep belief network pre-training algorithm is a robust and often helpful way to initialize deep neural networks generatively that can aid in optimization and reduce generalization error. We illustrate the key components of our model, describe the procedure for applying CD-DNN-HMMs to LVSR, and analyze the effects of various modeling choices on performance. Experiments on a challenging business search dataset demonstrate that CD-DNN-HMMs can significantly outperform the conventional context-dependent Gaussian mixture model (GMM)-HMMs, with an absolute sentence accuracy improvement of 5.8% and 9.2% (or relative error reduction of 16.0% and 23.2%) over the CD-GMM-HMMs trained using the minimum phone error rate (MPE) and maximum likelihood (ML) criteria, respectively.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: B Introduction To the Dnn-hmm Approachmentioning

confidence: 99%

Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition

Dahl

Deng

et al. 2012

IEEE Trans. Audio Speech Lang. Process.

Self Cite

2,631

1,175

View full text Add to dashboard Cite

show abstract

“…We evaluated our CD-DBN-HMM system by conducting a series of experiments on the data collected from the Bing mobile voice search (BMVS) application (formerly known as Live Search for mobile [14]) -a real-world, large-vocabulary, spontaneous, continuous speech recognition task.…”

Section: Methodsmentioning

confidence: 99%

Large vocabulary continuous speech recognition with context-dependent DBN-HMMS

Dahl

Deng

et al. 2011

2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

137

View full text Add to dashboard Cite

The context-independent deep belief network (DBN) hidden Markov model (HMM) hybrid architecture has recently achieved promising results for phone recognition. In this work, we propose a context-dependent DBN-HMM system that dramatically outperforms strong Gaussian mixture model (GMM)-HMM baselines on a challenging, large vocabulary, spontaneous speech recognition dataset from the Bing mobile voice search task. Our system achieves absolute sentence accuracy improvements of 5.8% and 9.2% over GMM-HMMs trained using the minimum phone error rate (MPE) and maximum likelihood (ML) criteria, respectively, which translate to relative error reductions of 16.0% and 23.2%.

show abstract

“…Our data come from the Windows Live Search for Mobile voice search task [19]. We divide the data into a 2.9M utterance (6.3M word) training set, 8.7K utterance (18.9K word) development set, and 12.7K utterance (27.2K word) test set.…”

Section: Datamentioning

confidence: 99%

Learning non-parametric models of pronunciation

Hutchinson

Droppo

2011

2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

As more data becomes available for a given speech recognition task, the natural way to improve recognition accuracy is to train larger models. But, while this strategy yields modest improvements to small systems, the relative gains diminish as the data and models grow. In this paper, we demonstrate that abundant data allows us to model patterns and structure that are unaccounted for in standard systems. In particular, we model the systematic mismatch between the canonical pronunciations of words and the actual pronunciations found in casual or accented speech. Using a combination of two simple data-driven pronunciation models, we can correct 5.2% of the errors in our mobile voice search application.

show abstract

Live search for mobile:Web services by voice on the cellphone

Cited by 55 publications

References 5 publications

Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition

Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition

Large vocabulary continuous speech recognition with context-dependent DBN-HMMS

Learning non-parametric models of pronunciation

Contact Info

Product

Resources

About