Exemplar-Based Sparse Representations for Noise Robust Automatic Speech Recognition
Open accessThe DOI matches its Crossref record; 21 of the 21 references it cites were found in a registry or an index.
Abstract
This paper proposes to use exemplar-based sparse representations for noise robust automatic speech recognition. First, we describe how speech can be modeled as a linear combination of a small number of exemplars from a large speech exemplar dictionary. The exemplars are time-frequency patches of real speech, each spanning multiple time frames. We then propose to model speech corrupted by additive noise as a linear combination of noise and speech exemplars, and we derive an algorithm for recovering this sparse linear combination of exemplars from the observed noisy speech. We describe how the framework can be used for doing hybrid exemplar-based/HMM recognition by using the exemplar-activations together with the phonetic information associated with the exemplars. As an alternative to hybrid recognition, the framework also allows us to take a source separation approach which enables exemplar-based feature enhancement as well as missing data mask estimation. We evaluate the performance of these exemplar-based methods in connected digit recognition on the AURORA-2 database. Our results show that the hybrid system performed substantially better than source separation or missing data mask estimation at lower signal-to-noise ratios (SNRs), achieving up to 57.1% accuracy at SNR = -5 dB. Although not as effective as two baseline recognizers at higher SNRs, the novel approach offers a promising direction of future research on exemplar-based ASR.
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
An Introduction To Compressive Sampling
Candes, E. J., & Wakin, M. B. (2008) · IEEE Signal Processing Magazine · doi:10.1109/msp.2007.914731 · Cited by 10,017 · cited 2×
“Thatsparserepresentation isdeterminedbyfindingthesparsestpossiblelinearcombination that describes the observed signal, using techniques best known from the fields of non-negative matrix factorization (NMF) [9] and compressed sensing [10].”
MethodALGORITHMS FOR NON-NEGATIVE MATRIX FACTORIZATION
Lee, D. D., & Seung, H. S. (2000) · neural information processing systems · Cited by 9,876
$rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation
Aharon, M., Elad, M., & Bruckstein, A. (2006) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2006.881199 · Cited by 9,451
Robust Face Recognition via Sparse Representation
Wright, J., Yang, A. Y., Ganesh, A., Sastry, S. S., & Ma, Y. (2009) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2008.79 · Cited by 9,388
ALGORITHMS FOR NON-NEGATIVE MATRIX FACTORIZATION
Seung, D., & Lee, L.-W. (2001) · Cited by 4,753
Pearce, D., & Hirsch, H.-G. (2000) · 6th International Conference on Spoken Language Processing (ICSLP 2000) · doi:10.21437/icslp.2000-743 · Cited by 1,772
Virtanen, T. (2007) · IEEE Transactions on Audio, Speech and Language Processing · doi:10.1109/tasl.2006.885253 · Cited by 1,005
Self-citationNon-negative matrix factorization for polyphonic music transcription
Smaragdis, P., & Brown, J. C. (2004) · 2003 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (IEEE Cat. No.03TH8684) · doi:10.1109/aspaa.2003.1285860 · Cited by 860
Robust continuous speech recognition using parallel model combination
Gales, M., & Young, S. J. (1996) · IEEE Transactions on Speech and Audio Processing · doi:10.1109/89.536929 · Cited by 439
On the Convergence of Multiplicative Update Algorithms for Nonnegative Matrix Factorization
Lin, C.-J. (2007) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2007.895831 · Cited by 416
Convolutive Speech Bases and Their Application to Supervised Speech Separation
Smaragdis, P. (2007) · IEEE Transactions on Audio, Speech and Language Processing · doi:10.1109/tasl.2006.876726 · Cited by 383
HMM adaptation using vector taylor series for noisy speech recognition
Acero, A., Deng, L., Kristjansson, T., & Zhang, J. (2000) · 6th International Conference on Spoken Language Processing (ICSLP 2000) · doi:10.21437/icslp.2000-672 · Cited by 278
Missing-feature approaches in speech recognition
Raj, B., & Stern, R. M. (2005) · IEEE Signal Processing Magazine · doi:10.1109/msp.2005.1511828 · Cited by 227
MVA Processing of Speech Features
Chen, C.-P., & Bilmes, J. A. (2007) · IEEE Transactions on Audio, Speech and Language Processing · doi:10.1109/tasl.2006.876717 · Cited by 211
Template-Based Continuous Speech Recognition
Wachter, M. D., Matton, M., Demuynck, K., Wambacq, P., Cools, R. F. A., & Compernolle, D. V. (2007) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/tasl.2007.894524 · Cited by 184
Towards increasing speech recognition error rates
Bourlard, H. A., Heřmanský, H., & Morgan, N. H. (1996) · Speech Communication · doi:10.1016/0167-6393(96)00003-9 · Cited by 174
Audio source separation with a single sensor
Benaroya, L., Bimbot, F., & Gribonval, R. (2006) · IEEE Transactions on Audio, Speech and Language Processing · doi:10.1109/tsa.2005.854110 · Cited by 169
Frey, B. J., Deng, L., Acero, A., & Kristjansson, T. T. (2001) · European Conference on Speech Communication and Technology (Eurospeech) · doi:10.21437/eurospeech.2001-273 · Cited by 96
Separation of Sound Sources by Convolutive Sparse Coding
Virtanen, T. I. (2004) · Cited by 73
Self-citationSparse coding for speech recognition
Sivaram, G. S. V. S., Nemala, S. K., Elhilali, M., Tran, T. D., & Heřmanský, H. (2010) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2010.5495649 · Cited by 73
Unsupervised learning of time–frequency patches as a noise-robust representation of speech
Segbroeck, M. V., & hamme, H. V. (2009) · Speech Communication · doi:10.1016/j.specom.2009.05.003 · Cited by 25
Cited by
An Overview of Noise-Robust Automatic Speech Recognition
Li, J., Deng, L., Gong, Y., & Haeb-Umbach, R. (2014) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2014.2304637 · Cited by 568
Machine Learning Paradigms for Speech Recognition: An Overview
Deng, L., & Li, X. (2013) · IEEE Transactions on Audio, Speech, and Language Processing · doi:10.1109/tasl.2013.2244083 · Cited by 456
(2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-72038-8 · Cited by 11
Metadata
- Authors
- Gemmeke, J. F., Virtanen, T., & Hurmalainen, A.
- Venue
- IEEE Transactions on Audio, Speech, and Language Processing
- Published
- 2011-09
- Volume
- 19
- Issue
- 7
- Pages
- 2067-2080
- ISSN
- 1558-7916 (ISSN-L)
- 1558-7924
- OpenAlex
- W2141520175
- Cited by
- 328
- References
- 21
- FWCI
- 41.99
- Type
- journal article
- 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.