The DOI matches its Crossref record; 26 of the 26 references it cites were found in a registry or an index.
English Conversational Telephone Speech Recognition by Humans and Machines
Open accessAbstract
One of the most difficult speech recognition tasks is accurate recognition of human to human communication. Advances in deep learning over the last few years have produced major speech recognition improvements on the representative Switchboard conversational corpus. Word error rates that just a few years ago were 14% have dropped to 8.0%, then 6.6% and most recently 5.8%, and are now believed to be within striking range of human performance. This then raises two issues - what IS human performance, and how far down can we still drive speech recognition error rates? A recent paper by Microsoft suggests that we have already achieved human performance. In trying to verify this statement, we performed an independent set of human performance measurements on two conversational tasks and found that human performance may be considerably better than what was earlier reported, giving the community a significantly harder goal to achieve. We also report on our own efforts in this area, presenting a set of acoustic and language modeling techniques that lowered the word error rate of our own English conversational telephone LVCSR system to the level of 5.5%/10.3% on the Switchboard/CallHome subsets of the Hub5 2000 evaluation, which - at least at the writing of this paper - is a new performance milestone (albeit not at what we measure to be human performance!). On the acoustic side, we use a score fusion of three models: one LSTM with multiple feature inputs, a second LSTM trained with speaker-adversarial multi-task learning and a third residual net (ResNet) with 25 convolutional layers and time-dilated convolutions. On the language modeling side, we use word and character LSTMs and convolutional WaveNet-style language models.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Identity mappings in deep residual networks
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_38 · Cited by 10,741
Identity Mappings in Deep Residual Networks
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · arXiv · doi:10.48550/arxiv.1603.05027 · Cited by 10,665
Domain-Adversarial Training of Neural Networks
Ganin, Y., Ustinova, E., Ajakan, H., Germain, P., Larochelle, H., Laviolette, F., Marchand, M., & Lempitsky, V. (2017) · Advances in Computer Vision and Pattern Recognition · doi:10.1007/978-3-319-58347-1_10 · Cited by 8,318
Zagoruyko, S., & Komodakis, N. (2016) · Procedings of the British Machine Vision Conference 2016 · doi:10.5244/c.30.87 · Cited by 7,244
WaveNet: a generative model for raw audio
Oord, A. V. D., Dieleman, S., Zen, H., Simonyan, K., Vinyals, O., Graves, A., Kalchbrenner, N., Senior, A., & Kavukcuoglu, K. (2016) · arXiv · doi:10.48550/arxiv.1609.03499 · Cited by 4,911
(1992) · doi:10.5555/176313.176316 · Cited by 2,892
Recurrent Neural Network Regularization
Zaremba, W., Sutskever, I., & Vinyals, O. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1409.2329 · Cited by 2,123
Cited by
Opportunities and obstacles for deep learning in biology and medicine
Ching, T., Himmelstein, D. S., Beaulieu-Jones, B. K., Kalinin, A. A., Do, B. T., Way, G. P., Ferrero, E., Agapow, P.-M., Zietz, M., Hoffman, M. M., et al. (2018) · Journal of The Royal Society Interface · doi:10.1098/rsif.2017.0387 · Cited by 2,310
Deep learning-based electroencephalography analysis: a systematic review
Roy, Y., Banville, H., Albuquerque, I., Gramfort, A., Falk, T. H., & Faubert, J. (2019) · Journal of Neural Engineering · doi:10.1088/1741-2552/ab260c · Cited by 1,532
Kolbaek, M., Yu, D., Tan, Z.-H., & Jensen, J. (2017) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2017.2726762 · Cited by 820
Artificial Intelligence and the Modern Productivity Paradox: A Clash of Expectations and Statistics
Brynjolfsson, E., Rock, D., & Syverson, C. (2017) · National Bureau of Economic Research · doi:10.3386/w24001 · Cited by 773
The Microsoft 2017 Conversational Speech Recognition System
Xiong, W., Wu, L., Alleva, F., Droppo, J., Huang, X., & Stolcke, A. (2018) · 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2018.8461870 · Cited by 472
A review of speaker diarization: Recent advances with deep learning
Park, T. J., Kanda, N., Dimitriadis, D., Han, K. J., Watanabe, S., & Narayanan, S. (2022) · Computer Speech & Language · doi:10.1016/j.csl.2021.101317 · Cited by 354
Self-citationThe Fifth 'CHiME' Speech Separation and Recognition Challenge: Dataset, Task and Baselines
Barker, J., Watanabe, S., Vincent, E., & Trmal, J. (2018) · Interspeech 2018 · doi:10.21437/interspeech.2018-1768 · Cited by 279
Adversarial Attacks Against Automatic Speech Recognition Systems via Psychoacoustic Hiding
Schonherr, L., Kohls, K., Zeiler, S., Holz, T., & Kolossa, D. (2019) · Proceedings 2019 Network and Distributed System Security Symposium · doi:10.14722/ndss.2019.23288 · Cited by 270
Toward Human Parity in Conversational Speech Recognition
Xiong, W., Droppo, J., Huang, X., Seide, F., Seltzer, M. L., Stolcke, A., Yu, D., & Zweig, G. (2017) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2017.2756440 · Cited by 245
Multimodal Multi-task Learning for Dimensional and Continuous Emotion Recognition
Chen, S., Jin, Q., Zhao, J., & Wang, S. (2017) · Proceedings of the 7th Annual Workshop on Audio/Visual Emotion Challenge · doi:10.1145/3133944.3133949 · Cited by 147
Kinoshita, K., Ochiai, T., Delcroix, M., & Nakatani, T. (2020) · ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp40776.2020.9053266 · Cited by 104
Using artificial intelligence to assess clinicians’ communication skills
Ryan, P., Luz, S., Albert, P., Vogel, C., Normand, C., & Elwyn, G. (2019) · BMJ · doi:10.1136/bmj.l161 · Cited by 69
Erdem, E., Kuyu, M., Yagcioglu, S., Frank, A., Parcalabescu, L., Plank, B., Babii, A., Turuta, O., Erdem, A., Calixto, I., et al. (2022) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.12918 · Cited by 54
Safety First: Conversational Agents for Health Care
Bickmore, T., Trinh, H., Asadi, R., & Olafsson, S. (2018) · Human–Computer Interaction Series · doi:10.1007/978-3-319-95579-7_3 · Cited by 50
Measuring the Accuracy of Automatic Speech Recognition Solutions
Kuhn, K., Kersken, V., Reuter, B., Egger, N., & Zimmermann, G. (2023) · ACM Transactions on Accessible Computing · doi:10.1145/3636513 · Cited by 44
“But only because ASR ofers a solution for the complex task of transcription, it is not necessarily accessible and enables DHH individuals to participate in various events.”
BackgroundMethodResultInfluentialOn the Limit of English Conversational Speech Recognition
Tüske, Z., Saon, G., & Kingsbury, B. (2021) · Interspeech 2021 · doi:10.21437/interspeech.2021-211 · Cited by 41
Self-citationHow Might We Create Better Benchmarks for Speech Recognition?
Aksënova, A., van Esch, D., Flynn, J., & Golik, P. (2021) · Proceedings of the 1st Workshop on Benchmarking: Past, Present and Future · doi:10.18653/v1/2021.bppf-1.4 · Cited by 25
All-in-One Transformer: Unifying Speech Recognition, Audio Tagging, and Event Detection
Moritz, N., Wichern, G., Hori, T., & Roux, J. L. (2020) · Interspeech 2020 · doi:10.21437/interspeech.2020-2757 · Cited by 20
“You don’t understand me!”: Comparing ASR Results for L1 and L2 Speakers of Swedish
Cumbal, R., Moell, B., Lopes, J., & Engwall, O. (2021) · Interspeech 2021 · doi:10.21437/interspeech.2021-2140 · Cited by 20
Extracting Cause of Death from Verbal Autopsy with Deep Learning interpretable methods
Blanco, A., Perez, A., Casillas, A., & Cobos, D. (2021) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2020.3005769 · Cited by 17
A Comprehensive Evaluation of Incremental Speech Recognition and Diarization for Conversational AI
Addlesee, A., Yu, Y., & Eshghi, A. (2020) · Proceedings of the 28th International Conference on Computational Linguistics · doi:10.18653/v1/2020.coling-main.312 · Cited by 15
Automatic Speech Recognition: Do Emotions Matter?
Catania, F., Crovari, P., Spitale, M., & Garzotto, F. (2019) · 2019 IEEE International Conference on Conversational Data & Knowledge Engineering (CDKE) · doi:10.1109/cdke46621.2019.00009 · Cited by 7
Metadata
- Authors
- Saon, G., Kurata, G., Sercu, T., Audhkhasi, K., Thomas, S., Dimitriadis, D., Cui, X., Ramabhadran, B., Picheny, M., Lim, L.-L., Roomi, B., & Hall, P.
- Venue
- Interspeech 2017
- Publisher
- ISCA
- Published
- 2017-08-20
- Pages
- 132-136
- ISSN
- 2308-457X (ISSN-L)
- OpenAlex
- W2604132379
- Cited by
- 349
- References
- 26
- FWCI
- 30.23
- Type
- conference paper
- Language
- en
- Open access
- green
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.