The DOI matches its Crossref record; 107 of the 107 references it cites were found in a registry or an index; none of the 39 sources its claims cite is checked for support yet.
Speaker Adaptation Using Spectro-Temporal Deep Features for Dysarthric and Elderly Speech Recognition
Open accessAbstract
Despite the rapid progress of automatic speech recognition (ASR) technologies targeting normal speech in recent decades, accurate recognition of dysarthric and elderly speech remains highly challenging tasks to date. Sources of heterogeneity commonly found in normal speech including accent or gender, when further compounded with the variability over age and speech pathology severity level, create large diversity among speakers. To this end, speaker adaptation techniques play a key role in personalization of ASR systems for such users. Motivated by the spectro-temporal level differences between dysarthric, elderly and normal speech that systematically manifest in articulatory imprecision, decreased volume and clarity, slower speaking rates and increased dysfluencies, novel spectro-temporal subspace basis deep embedding features derived using SVD speech spectrum decomposition are proposed in this paper to facilitate auxiliary feature based speaker adaptation of state-of-the-art hybrid DNN/TDNN and end-to-end Conformer speech recognition systems. Experiments were conducted on four tasks: the English UASpeech and TORGO dysarthric speech corpora; the English DementiaBank Pitt and Cantonese JCCOCC MoCA elderly speech datasets. The proposed spectro-temporal deep feature adapted systems outperformed baseline i-Vector and x-Vector adaptation by up to 2.63% absolute (8.63% relative) reduction in word error rate (WER). Consistent performance improvements were retained after model based speaker adaptation using learning hidden unit contributions (LHUC) was further applied. The best speaker adapted system using the proposed spectral basis embedding features produced the lowest published WER of 25.05% on the UASpeech test set of 16 dysarthric speakers.
Overview
CoChat Summary
TL;DR
This paper proposes spectro-temporal deep embedding features, derived from SVD-based speech spectrum decomposition and bottleneck DNN classifiers, for speaker adaptation in dysarthric and elderly speech recognition. Across four tasks, the adapted ASR systems outperform i-Vector/x-Vector baselines, with the best reported UASpeech system reaching 25.05% WER.
Key findings
- On the English UASpeech corpus, the proposed spectral basis embedding (SBE) adapted systems reduced overall WER by up to 2.63% absolute (8.63% relative) versus conventional i-Vector/x-Vector adaptation, and the best speaker-adapted system achieved 25.05% WER on the 16-speaker test set.
- On the TORGO corpus, SBE-adapted TDNN systems improved over i-Vector adaptation by up to 1.27% absolute (14% relative) overall WER, and the SBE-adapted Conformer improved by 1.98% absolute (14.01% relative).
- On the DementiaBank Pitt corpus, SBE-adapted hybrid TDNN systems improved over i-Vector adaptation by up to 2.57% absolute (8.1% relative) overall WER, and the SBE-adapted Conformer improved by 1.38% absolute (4.21% relative).
- On the JCCOCC MoCA corpus, SBE-adapted hybrid TDNN systems improved over i-Vector adaptation by up to 1.07% absolute (4.44% relative) overall WER, and the SBE-adapted Conformer improved by 1.38% absolute (4.21% relative).
Methods
- The paper decomposes mel-spectrograms with SVD into spectral and temporal basis vectors, then trains DNN classifiers on these bases to predict speech severity/age labels; the 25-dimensional bottleneck outputs are used as speaker embeddings.
- Experiments use UASpeech and TORGO for dysarthric speech, and DementiaBank Pitt and JCCOCC MoCA for elderly speech, with data augmentation via speed perturbation and ASR systems including hybrid DNN, LF-MMI TDNN, and E2E Conformer.
- Main comparisons are against i-Vector and x-Vector adaptation, with optional LHUC on top of auxiliary-feature adaptation; performance is measured in WER (and CER for JCCOCC MoCA).
Limitations
- The paper states that SVD spectrum decomposition is performed in an unsupervised fashion, and that it is theoretically nontrivial to produce a perfect disentanglement between time-invariant and time-variant characteristics.
- It explicitly notes that using both spectral and temporal embedding features (SBE+TBE) did not give a consistent benefit over spectral features alone in the dysarthric speech experiments, so the remaining experiments use SBE only.
- Evident from the text: the paper’s gains are demonstrated on a limited set of four corpora and under specific experimental setups (selected models, language models, and augmentation), so generalization beyond these settings is not directly shown.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
0 Valid · 0 Not valid · 24 Not checked · 35 Own results and interpretations
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The proposed spectro-temporal deep feature adapted systems outperformed baseline i-Vector and xVector adaptation by up to 2.63% absolute (8.63% relative) reduction in word error rate (WER).”
- Also stated in: § B. Speaker Adaptation for Dysarthric and Elderly Speech · plain
“The proposed spectro-temporal deep feature adapted systems achieve statistically significant performance improvements over baseline i-Vector or x-Vector adapted hybrid DNN/TDNN and end-to-end (E2E) Conformer systems by up to 2 . 63% absolute ( 8 . 63% relative) word error rate (WER) reduction on four dysarthric or elderly speech recognition tasks across two languages.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § B. Speaker Adaptation for Dysarthric and Elderly Speech · plain
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The best speaker adapted system using the proposed spectral basis embedding features produced the lowest published WER of 25.05% on the UASpeech test set of 16 dysarthric speakers.”
- Also stated in: § B. Speaker Adaptation for Dysarthric and Elderly Speech · plain
“The best speaker adapted system using the proposed spectral basis embedding features produced the lowest published WER of 25 . 05% on the UASpeech test set of 16 dysarthric speakers.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § B. Speaker Adaptation for Dysarthric and Elderly Speech · plain
In the paper
“Speech pathology severity and age prediction performance as well as further visualization using t-distributed stochastic neighbor embedding (t-SNE) [87] indicate that our proposed spectro-temporal deep features can more effectively learn the speaker-level variability attributed to speech impairment severity and age than conventional i-Vector [56] and x-Vector [86].”
What the sources say
- Not matchedcites [87] [87] L. Van der Maaten et al. , 'Visualizing data using t-SNE,' J MACH LEARN RES , vol. 9, no. 11, 2008. -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
hedgedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Consistent performance improvements were retained after model based speaker adaptation using learning hidden unit contributions (LHUC) was further applied.”
- Also stated in: § B. Speaker Adaptation for Dysarthric and Elderly Speech · plain
“Consistent performance improvements were retained after model based speaker adaptation using learning hidden unit contributions (LHUC) was further applied.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § B. Speaker Adaptation for Dysarthric and Elderly Speech · plain
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The SBE adapted E2E Conformer system outperformed its i-Vector baseline statistically significantly by 1 . 38% absolute ( 4 . 21% relative) (Sys.12 v.s. Sys.10).”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
34 more claims
Create a free account to see all 59 claims and to verify the 23 references still open.
- It may state two separate claims as one. 10
- Probably not a substantial claim. 11
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
“Of the 30 included studies, 6 performed model-centric explainability validation using external data [4719555658], including 1 study [19] that explicitly assessed the cross-language consistency of explanation patterns.”
From Explainable and Interpretable AI for Voice and Speech Analysis in Clinical Care: Systematic Review (2026) · cites this paper as [19]
Citations
Cites
(2008) · Journal of Machine Learning Research · Cited by 33,051
(2003) · Journal of Machine Learning Research · doi:10.5555/944919.944937 · Cited by 32,337
Learning the parts of objects by non-negative matrix factorization
Lee, D. D., & Seung, H. S. (1999) · Nature · doi:10.1038/44565 · Cited by 13,868
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
Kaldi Speech Recognition Toolkit
Povey, D. (2024) · Infoscience (Ecole Polytechnique Fédérale de Lausanne) · doi:10.57702/jb3fvbn9 · Cited by 4,609
SRILM - an extensible language modeling toolkit
Stolcke, A. (2002) · 7th International Conference on Spoken Language Processing (ICSLP 2002) · doi:10.21437/icslp.2002-303 · Cited by 4,326
2013 Alzheimer's disease facts and figures
Alzheimer's Association, Thies, W., & Bleiler, L. (2013) · Alzheimer's & Dementia · doi:10.1016/j.jalz.2013.02.003 · Cited by 3,328
Conformer: Convolution-augmented Transformer for Speech Recognition
Gulati, A., Qin, J., Chiu, C.-C., Parmar, N., Zhang, Y., Yu, J., Han, W., Wang, S., Zhang, Z., Wu, Y., et al. (2020) · Interspeech 2020 · doi:10.21437/interspeech.2020-3015 · Cited by 3,150
Conformer: Convolution-augmented Transformer for Speech Recognition
Gulati, A., Qin, J., Chiu, C.-C., Parmar, N., Zhang, Y., Yu, J., Han, W., Wang, S., Zhang, Z., Wu, Y., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.08100 · Cited by 3,150
(1994) · Knowledge Discovery and Data Mining · Cited by 3,137
Research works printed but not linked: 4
- lanier, 2010, J Speech Disorders
- young, 2002, The HTK Book, 3
- locatello, 2020, A sober look at the unsupervised learning of disentangled representations and their evaluation, J Mach Learn Res, 21, 1
- xu, 0, Speaker turn aware similarity scoring for diarization of speech-based cognitive assessments, Proc IEEE Asia-Pacific Signal Inf Process Assoc Annu Summit Conf, 1299
Cited by
Brahmi, Z., Mahyoob, M., Al-Sarem, M., Algaraady, J., Bousselmi, K., & Alblwi, A. (2024) · Psychology Research and Behavior Management · doi:10.2147/prbm.s460283 · Cited by 36
Speaking of accent: A content analysis of accent misconceptions in ASR research
Prinos, K., Patwari, N., & Power, C. A. (2024) · The 2024 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3630106.3658969 · Cited by 12
Explainable and Interpretable AI for Voice and Speech Analysis in Clinical Care: Systematic Review
Ebraheem, M., Toghranegar, J., Bridge2AI-Voice Consortium, Bensoussan, Y., & Templeton, J. M. (2026) · Journal of Medical Internet Research · doi:10.2196/83790
Metadata
- Authors
- Geng, M., Xie, X., Ye, Z., Wang, T., Li, G., Hu, S., Liu, X., & Meng, H.
- Affiliations
- Chinese University of Hong Kong (HK)
- Chinese Academy of Sciences (CN)
- Venue
- IEEE/ACM Transactions on Audio Speech and Language Processing
- Published
- 2022
- Volume
- 30
- Pages
- 2597-2611
- ISSN
- 2329-9290 (ISSN-L)
- 2329-9304
- OpenAlex
- W4221162789
- Cited by
- 48
- References
- 107
- Citations by year
- 2026: 12 · 2025: 21 · 2024: 8 · 2023: 7
- FWCI
- 2.96
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE/ACM Transactions on Audio Speech and Language Processing (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Hong Kong Research Council GRF (14200218, 14200220, 14200021)
- Theme based Research Scheme (T45-407/19 N)
- Innovation and Technology Fund (ITS/254/19)
- National Natural Science Foundation of China (62106255)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
- Health Sciences › Health Professions › Speech and Hearing › Voice and Speech Disorders
- Keywords
- speaker adaptation, dysarthric speech recognition, conformational isomers, speech-language pathology
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.
A language model drew the claims from the paper on 2026-10-11, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-11 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
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: Speaker Adaptation Using Spectro-Temporal Deep Features for Dysarthric and Elderly Speech Recognition. https://app.cochat.ai/papers/10.1109/taslp.2022.3195113
- The paper
- Geng, M., Xie, X., Ye, Z., Wang, T., Li, G., Hu, S., Liu, X., & Meng, H. (2022). Speaker Adaptation Using Spectro-Temporal Deep Features for Dysarthric and Elderly Speech Recognition. IEEE/ACM Transactions on Audio Speech and Language Processing. https://doi.org/10.1109/taslp.2022.3195113
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.