Extending Parrotron: An End-to-End, Speech Conversion and Speech Recognition Model for Atypical Speech
The DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Abstract
We present an extended Parrotron model: a single, end-to-end network that enables voice conversion and recognition simultaneously. Input spectrograms are transformed to output spectrograms in the voice of a predetermined target speaker while also generating hypotheses in a target vocabulary. We study the performance of this novel architecture, which jointly predicts speech and text, on atypical (e.g. dysarthric) speech. We show that with as little as an hour of atypical speech, speaker adaptation can yield a 77% relative reduction in Word Error Rate (WER), measured by ASR performance on the converted speech. We also show that data augmentation using a customized synthesizer built on atypical speech can provide an additional 10% relative improvement over the best speaker-adapted model. Finally, we show how these methods generalize across 8 types of atypical speech for a range of speech impairment severities.
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
“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
SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
Park, D. S., Chan, W., Zhang, Y., Chiu, C.-C., Zoph, B., Cubuk, E. D., & Le, Q. V. (2019) · Interspeech 2019 · doi:10.21437/interspeech.2019-2680 · Cited by 3,558
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
A voice-input voice-output communication aid for people with severe speech impairment
Hawley, M. S., Cunningham, S. P., Green, P. D., Enderby, P., Palmer, R., Sehgal, S., & O'Neill, P. (2013) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2012.2209678 · Cited by 110
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×
“Thus, speaker adaptation and speaker-specific pronunciation methods from conventional ASR can apply, which is why we see up to 40% relative gains in ASR WER on dysarthric speech [15].”
Method
Research works printed but not linked: 25
- 10.21437/Interspeech.2019-2277 · DOI
- 10.1109/ICASSP40776.2020.9054596 · DOI
- 10.1109/JBHI.2019.2961844 · DOI
- 10.21437/Interspeech.2019-1752 · DOI · Paper page
- 10.21437/Interspeech.2018-67 · DOI
- 10.1109/ICCSIT.2009.5234947 · DOI
- 10.1109/ICASSP.2018.8462290 · DOI
- 10.21437/Interspeech.2018-1751 · DOI · Paper page
- 10.1109/ICASSP.2019.8683091 · DOI · Paper page
- 10.1250/ast.33.1 · DOI · Paper page
- biadsy, 2017, Effectively building tera scale maxent language models incorporating nonlinguistic signals, InterSpeech, 2710, 10.21437/Interspeech.2017-1203 · DOI
- 10.1016/j.specom.2005.08.001 · doi:10.1016/j.specom.2005.08.001
- 10.1016/j.specom.2007.05.001 · DOI · Paper page
- 10.21437/Interspeech.2019-1206 · DOI
- 10.5220/0009163003080313 · doi:10.5220/0009163003080313
- 10.1109/TASSP.1984.1164317 · DOI · Paper page
- 10.21437/Interspeech.2019-1265 · doi:10.21437/interspeech.2019-1265
- 10.21437/Interspeech.2019-1789 · DOI · Paper page
- 10.1109/ICASSP40776.2020.9053725 · DOI
- 10.21437/Interspeech.2019-1427 · DOI · Paper page
- 10.21437/Interspeech.2019-3161 · DOI · Paper page
- 10.1109/ICASSP40776.2020.9054476 · DOI · Paper page
- vaswani, 2017, Attention is all you need, Neural Information Processing Systems, 6000
- 10.1109/ICASSP.2018.8461368 · DOI · Paper page
- 10.1109/ASRU46091.2019.9003990 · DOI
Cited by
Generative AI applied to AAC for aphasia: a pilot study of Aphasia-GPT
Bailey, D. J., Herget, F., Hansen, D., Burton, F., Pitt, G., Harmon, T., & Wingate, D. (2026) · Aphasiology · doi:10.1080/02687038.2024.2445663 · Cited by 13
Metadata
- Authors
- Doshi, R., Chen, Y., Jiang, L., Zhang, X., Biadsy, F., Ramabhadran, B., Chu, F., Rosenberg, A., & Moreno, P. J.
- Venue
- ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- Publisher
- IEEE
- Published
- 2021-06-06
- Pages
- 6988-6992
- Cited by
- 22
- References
- 5
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Extending Parrotron: An End-to-End, Speech Conversion and Speech Recognition Model for Atypical Speech. https://app.cochat.ai/papers/10.1109/icassp39728.2021.9414644
- The paper
- Doshi, R., Chen, Y., Jiang, L., Zhang, X., Biadsy, F., Ramabhadran, B., Chu, F., Rosenberg, A., & Moreno, P. J. (2021). Extending Parrotron: An End-to-End, Speech Conversion and Speech Recognition Model for Atypical Speech. ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https://doi.org/10.1109/icassp39728.2021.9414644
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.