Longitudinal study of ASR performance on ageing voices
Open accessAbstract
This paper presents the results of a longitudinal study of ASR performance on ageing voices. Experiments were conducted on the audio recordings of the proceedings of the Supreme Court Of The United States (SCOTUS). Results show that the Automatic Speech Recognition (ASR) Word Error Rates (WERs) for elderly voices are significantly higher than those of adult voices. The word error rate increases gradually as the age of the elderly speakers increase. Use of maximum likelihood linear regression (MLLR) based speaker adaptation on ageing voices improves the WER though the performance is still considerably lower compared to adult voices. Speaker adaptation however reduces the increase in WER with age during old age.
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
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?
Performance of recognition systems decreases steadily with age, and special adaptation to each speaker can produce scores similar to those obtained from the youngest speakers without adaptation.
“Nevertheless, these studies show that the performance of recognition systems decreases steadily with age, and also that special adaptation to each speaker can produce scores similar to those obtained from the youngest speakers without adaptation.”
From Making Emergency Calls More Accessible to Older Adults Through a Hands-free Speech Interface in the House (2019) · cites this paper as Vipperla et al., 2008
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Acoustic models of the elderly for large-vocabulary continuous speech recognition
Baba, A., Yoshizawa, S., Yamada, M., Lee, A., & Shikano, K. (2004) · Electronics and Communications in Japan (Part II Electronics) · doi:10.1002/ecjb.20101 · Cited by 45 · see citing works
Flagged first, then by citations
Research works printed but not linked: 4
- Xue, S, A., and Hao G. J., "Changes in human vocal tract due to aging and the acoustic correlates of speech production: a pi- lot study", Journal of Speech, Language and Hearing Research, 46(3):689-701, 2003
- Wilpon, J. G., and Nacobsen, C. N., "A study of speech recog- nition for children and the elderly", in Proceedings of the Inter- national Conference on Acoustics, Speech and Signal Processing, IEEE Press: 349-352, 1996.
- Anderson, S., Liberman, N., Bernstein, E., Foster, S., Cate, E., and Levin, B., "Recognition of elderly speech and voice driven docu- ment retrieval", Proc IEEE International Conference on Acoustics Speech and Signal Processing, 1:145-148, 1999
- Yuan, J., and Liberman, M.,"Speaker identification on the SCO- TUS corpus", Accepted for proceedings of ASA 2008
Cited by
Sorted by citations
A Review of Automated Speech and Language Features for Assessment of Cognitive and Thought Disorders
Voleti, R., Liss, J. M., & Berisha, V. (2020) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2019.2952087 · Cited by 96 · see citing works
Vacher, M., Caffiau, S., Portet, F., Meillon, B., Roux, C., Elias, E., Lecouteux, B., & Chahuara, P. (2015) · ACM Transactions on Accessible Computing · doi:10.1145/2738047 · Cited by 73 · see citing works
Speech Recognition in Alzheimer’s Disease and in its Assessment
Zhou, L., Fraser, K. C., & Rudzicz, F. (2016) · Interspeech 2016 · doi:10.21437/interspeech.2016-1228 · Cited by 62 · see citing works
Speech Input from Older Users in Smart Environments: Challenges and Perspectives
Vipperla, R., Wolters, M., Georgila, K., & Renals, S. (2009) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-02710-9_14 · Cited by 37 · see citing works
Self-citationVacher, M., Aman, F., Rossato, S., Portet, F., & Lecouteux, B. (2019) · ACM Transactions on Accessible Computing · doi:10.1145/3310132 · Cited by 10 · see citing works
- Authors
- Vipperla, R., Renals, S., & Frankel, J.
- Affiliations
- University of Edinburgh (GB)
- ORCID
- Renals, Steve
- Venue
- Interspeech 2008
- Publisher
- ISCA
- Published
- 2008-09-22
- Pages
- 2550-2553
- ISSN
- 2308-457X (ISSN-L)
- OpenAlex
- W1574317991
- Cited by
- 75
- References
- 1
- Citations by year
- 2026: 3 · 2025: 5 · 2024: 3 · 2023: 5 · 2022: 6 · 2021: 2 · 2020: 3 · 2019: 7 · 2018: 4 · 2017: 2 · 2016: 3 · 2015: 7 · 2014: 7 · 2013: 7 · 2012: 7
- FWCI
- 0.98
- Type
- conference paper
- Language
- en
- Open access
- green
- hdl.handle.net
- Locations
- Interspeech (USB) (publishedVersion)
- ERA (submittedVersion)
- Edinburgh Research Explorer (University of Edinburgh) (submittedVersion, other-oa)
- Funders
- Scottish Funding Council
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Keywords
- speech recognition, elderly speakers, word error rate, speaker adaptation, maximum likelihood linear regression, longitudinal study
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
