Personalizing ASR for Dysarthric and Accented Speech with Limited Data
Open accessThe DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Abstract
Automatic speech recognition (ASR) systems have dramatically improved over the last few years. ASR systems are most often trained from 'typical' speech, which means that underrepresented groups don't experience the same level of improvement. In this paper, we present and evaluate finetuning techniques to improve ASR for users with non-standard speech. We focus on two types of non-standard speech: speech from people with amyotrophic lateral sclerosis (ALS) and accented speech. We train personalized models that achieve 62% and 35% relative WER improvement on these two groups, bringing the absolute WER for ALS speakers, on a test set of message bank phrases, down to 10% for mild dysarthria and 20% for more serious dysarthria. We show that 71% of the improvement comes from only 5 minutes of training data. Finetuning a particular subset of layers (with many fewer parameters) often gives better results than finetuning the entire model. This is the first step towards building state of the art ASR models for dysarthric speech.
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
Speech recognition with deep recurrent neural networks
Graves, A., Mohamed, A.-R., & Hinton, G. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6638947 · Cited by 8,893 · cited 2×
“The RNN-Transducer [6, 7] is a neural network architecture that has shown good results on numerous ASR tasks.”
“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
How transferable are features in deep neural networks?
Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014) · arXiv · doi:10.48550/arxiv.1411.1792 · Cited by 6,061 · cited 1×
“Many computer vision papers publish good results by finetuning the last few layers of a classification network that was pretrained on Imagenet [28].”
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
Adapting acoustic and lexical models to dysarthric speech
Mengistu, K. T., & Rudzicz, F. (2011) · 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2011.5947460 · Cited by 82 · cited 1×
“There are a number of methods for adapting large ASR models to small amounts of data [12, 13, 14].”
Cited by
Widening Access to Applied Machine Learning with TinyML
Janapa Reddi, V., Plancher, B., Kennedy, S., Moroney, L., Warden, P., Suzuki, L., Agarwal, A., Banbury, C., Banzi, M., Bennett, M., et al. (2022) · Harvard Data Science Review · doi:10.1162/99608f92.762d171a · Cited by 62
Geng, M., Xie, X., Ye, Z., Wang, T., Li, G., Hu, S., Liu, X., & Meng, H. (2022) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2022.3195113 · Cited by 48
Deep learning applications in telerehabilitation speech therapy scenarios
Mulfari, D., La Placa, D., Rovito, C., Celesti, A., & Villari, M. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.105864 · Cited by 41
How 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
“However, given the high degree of variability in this space, a more robust path at least for the near-term future may be designing personalized ASR systems for people with non-standard speech (Shor et al., 2019).”
BackgroundOn-device personalization of automatic speech recognition models for disordered speech
Tomanek, K., Beaufays, F., Cattiau, J., Chandorkar, A., & Sim, K. C. (2021) · arXiv · doi:10.48550/arxiv.2106.10259 · Cited by 14
Self-citation
Metadata
- Authors
- Shor, J., Emanuel, D., Lang, O., Tuval, O., Brenner, M., Cattiau, J., Vieira, F., McNally, M., Charbonneau, T., Nollstadt, M., Hassidim, A., & Matias, Y.
- Venue
- Interspeech 2019
- Publisher
- ISCA
- Published
- 2019-09-15
- Pages
- 784-788
- ISSN
- 2308-457X (ISSN-L)
- OpenAlex
- W2964525587
- Cited by
- 114
- References
- 5
- FWCI
- 5.01
- 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.