Abstract / Description of output
In this paper, we introduce a newly-created corpus of whispered speech simultaneously recorded via a close-talking microphone and a non-audible murmur (NAM) microphone in both clean and noisy conditions. To benchmark the corpus, which has been freely released recently, experiments on automatic recognition of continuous whispered speech were conducted. When training and test conditions are matched, the NAM microphone is found to be more robust against background noise than the close-talking microphone. In mismatched conditions (noisy data, models trained on clean speech), we found that Vector Taylor Series (VTS) compensation is particularly effective for the NAM signal.
| Original language | English |
|---|---|
| Title of host publication | Chinese Spoken Language Processing (ISCSLP), 2012 8th International Symposium on |
| Publisher | Institute of Electrical and Electronics Engineers |
| Pages | 220-223 |
| Number of pages | 4 |
| ISBN (Electronic) | 978-1-4673-2505-9 |
| DOIs | |
| Publication status | Published - 4 Dec 2012 |
Keywords / Materials (for Non-textual outputs)
- microphones
- speech recognition
- NAM microphone
- VTS compensation
- clean conditions
- close-talking microphone
- noise-robust whispered speech recognition
- noisy conditions
- non-audible-murmur microphone
- vector Taylor series compensation
- Acoustics
- Hidden Markov models
- Microphones
- Noise
- Noise measurement
- Speech
- Speech recognition
- noise robustness
- non-audible murmur (NAM)
- silent speech interface (SSI)
- vector Taylor series (VTS)
- whisper recognition
Fingerprint
Dive into the research topics of 'Noise-robust whispered speech recognition using a non-audible-murmur microphone with VTS compensation'. Together they form a unique fingerprint.Datasets
-
CSTR NAM TIMIT Plus
Clark, R. (Creator), King, S. (Creator), Yang, C. (Creator), Yamagishi, J. (Creator) & Brown, G. (Creator), Edinburgh DataShare, 2 Mar 2021
DOI: 10.7488/ds/2994
Dataset