The DOI matches its Crossref record; 21 of the 21 references it cites were found in a registry or an index.
Neural Speech Recognizer: Acoustic-to-Word LSTM Model for Large Vocabulary Speech Recognition
Open accessAbstract
We present results that show it is possible to build a competitive, greatly simplified, large vocabulary continuous speech recognition system with whole words as acoustic units. We model the output vocabulary of about 100,000 words directly using deep bi-directional LSTM RNNs with CTC loss. The model is trained on 125,000 hours of semi-supervised acoustic training data, which enables us to alleviate the data sparsity problem for word models. We show that the CTC word models work very well as an end-to-end all-neural speech recognition model without the use of traditional context-dependent sub-word phone units that require a pronunciation lexicon, and without any language model removing the need to decode. We demonstrate that the CTC word models perform better than a strong, more complex, state-of-the-art baseline with sub-word units.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Additionally, Soltau et al. (2017) have proved that a simple end-to-end model can produce better results when trained with large-scale data, compared with a complex model trained with small-scale data.”
From MOPRD: A multidisciplinary open peer review dataset (2022) · cites this paper as Soltau et al. (2017)
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Bidirectional recurrent neural networks
Schuster, M., & Paliwal, K. K. (1997) · IEEE Transactions on Signal Processing · doi:10.1109/78.650093 · Cited by 10,172
“Librispeech: an ASR corpus based on public domain audio books,”
Panayotov, V., Chen, G., Povey, D., & Khudanpur, S. (2015) · 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2015.7178964 · Cited by 6,072
Large Scale Distributed Deep Networks
Dean, J. B., Corrado, G. S., Monga, R., Chen, K., Devin, M., Mao, M., Ranzato, M., Senior, A., Tucker, P. A., Yang, K., et al. (2012) · Cited by 3,202
Long short-term memory recurrent neural network architectures for large scale acoustic modeling
Sak, H., Senior, A., & Beaufays, F. (2014) · Interspeech 2014 · doi:10.21437/interspeech.2014-80 · Cited by 2,973
Self-citationDeep Speech 2: End-to-End Speech Recognition in English and MandarinPreprint
Amodei, D., Anubhai, R., Battenberg, E., Case, C. T., Casper, J., Catanzaro, B., Chen, J., Chrzanowski, M., Coates, A., Diamos, G., et al. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1512.02595 · Cited by 2,265
Listen, attend and spell: A neural network for large vocabulary conversational speech recognition
Chan, W., Jaitly, N., Le, Q., & Vinyals, O. (2016) · 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2016.7472621 · Cited by 2,226
Towards End-To-End Speech Recognition with Recurrent Neural Networks
Graves, A., & Jaitly, N. (2014) · Cited by 1,861
End-to-end attention-based large vocabulary speech recognition
Bahdanau, D., Chorowski, J., Serdyuk, D., Brakel, P., & Bengio, Y. (2016) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2016.7472618 · Cited by 1,161
EESEN: End-to-end speech recognition using deep RNN models and WFST-based decoding
Miao, Y., Gowayyed, M. A., & Metze, F. (2015) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru.2015.7404790 · Cited by 727
Tree-based state tying for high accuracy acoustic modelling
Young, S. J., Odell, J. J., & Woodland, P. C. (1994) · doi:10.3115/1075812.1075885 · Cited by 673
A time-delay neural network architecture for isolated word recognition
Lang, K. J., Waibel, A., & Hinton, G. E. (1990) · Neural Networks · doi:10.1016/0893-6080(90)90044-l · Cited by 600
Fast and accurate recurrent neural network acoustic models for speech recognition
Sak, H., Senior, A., Rao, K., & Beaufays, F. (2015) · Interspeech (USB) · doi:10.21437/interspeech.2015-350 · Cited by 426
Self-citationTowards End-to-End Speech Recognition with Deep Convolutional Neural Networks
Zhang, Y., Pezeshki, M., Brakel, P., Zhang, S., Laurent, C., Bengio, Y., & Courville, A. C. (2016) · Interspeech (USB) · doi:10.21437/interspeech.2016-1446 · Cited by 419
Liao, H., McDermott, E., & Senior, A. (2013) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru.2013.6707758 · Cited by 188
Self-citationLearning acoustic frame labeling for speech recognition with recurrent neural networks
Sak, H., Senior, A., Rao, K., İrsoy, O., Graves, A., Beaufays, F., & Schalkwyk, J. (2015) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2015.7178778 · Cited by 176
Self-citationLu, L., Zhang, X., & Renals, S. J. (2016) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2016.7472641 · Cited by 125
Context dependent phone models for LSTM RNN acoustic modelling
Senior, A., Sak, H., & Izhak Shafran, J. (2015) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2015.7178839 · Cited by 52
Self-citationLanguage model verbalization for automatic speech recognition
Sak, H., Beaufays, F., Nakajima, K., & Allauzen, C. (2013) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2013.6639276 · Cited by 29
Self-citationA big data approach to acoustic model training corpus selection
Kapralova, O., Alex, J. S. R., Weinstein, E., Moreno, P. J., & Siohan, O. (2014) · Interspeech (USB) · doi:10.21437/interspeech.2014-473 · Cited by 27
Learning N-Gram Language Models from Uncertain Data
Kuznetsov, V., Liao, H., Mohri, M., Riley, M., & Brian Roark, A. (2016) · Interspeech (USB) · doi:10.21437/interspeech.2016-1093 · Cited by 16
Self-citation
Research works printed but not linked: 2
- L.R. Bahl, P.V. de Souza, P.S. Gopalakrishnan, D. Nahamoo, and M.A. Picheny. Context dependent modelling of phones in continuous speech using decision trees. In Proc. DARPA Speech and Natural Language Processing Workshop, 1991.
- Alex Graves, Santiago Fernández, Faustino Gomez, and Jürgen Schmidhuber. Connectionist temporal classification: Labelling unsegmented sequence data with recurrent neural networks. In Proc. ICML, 2006.
Cited by
Sorted by citations
A State-of-the-Art Survey on Deep Learning Theory and Architectures
Alom, M. Z., Taha, T. M., Yakopcic, C., Westberg, S. K. E., Sidike, P., Nasrin, M. S., Hasan, M., Essen, B. C. V., Awwal, A. A. S., & Asari, V. K. (2019) · Electronics · doi:10.3390/electronics8030292 · Cited by 1,722
Micikevicius, P., Narang, S., Alben, J., Diamos, G., Elsen, E., Garcia, D., Ginsburg, B., Houston, M., Kuchaiev, O., Venkatesh, G., et al. (2017) · arXiv · doi:10.48550/arxiv.1710.03740 · Cited by 1,179
Deep Learning for Audio Signal Processing
Purwins, H., Li, B., Virtanen, T. I., Schlüter, J., Chang, S.-Y., & Sainath, T. N. (2019) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2019.2908700 · Cited by 929
Hybrid CTC/Attention Architecture for End-to-End Speech Recognition
Watanabe, S., Hori, T., Kim, S., Hershey, J. R., & Hayashi, T. (2017) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2017.2763455 · Cited by 810
Streaming End-to-end Speech Recognition for Mobile Devices
He, Y., Sainath, T. N., Prabhavalkar, R., McGraw, I., Alvarez, R., Zhao, D., Rybach, D., Kannan, A., Wu, Y., Pang, R., et al. (2019) · ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2019.8682336 · Cited by 601
Metadata
- Authors
- Soltau, H., Liao, H., & Sak, H.
- Affiliations
- Google (United States) (US)
- Venue
- Interspeech 2017
- Publisher
- ISCA
- Published
- 2017-08-20
- Pages
- 3707-3711
- ISSN
- 2308-457X (ISSN-L)
- OpenAlex
- W2545177271
- Cited by
- 304
- References
- 21
- Citations by year
- 2025: 9 · 2024: 6 · 2023: 26 · 2022: 25 · 2021: 37 · 2020: 39 · 2019: 73 · 2018: 58 · 2017: 31
- FWCI
- 25.07
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- public-domain
- Locations
- Interspeech (USB) (publishedVersion)
- arXiv (Cornell University) (submittedVersion, public-domain)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Phonetics and Phonology Research
- Keywords
- large vocabulary continuous speech recognition, bidirectional LSTM, CTC loss, data sparsity, pronunciation dictionary
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
