The DOI matches its Crossref record; 28 of the 28 references it cites were found in a registry or an index.
On Training Targets for Supervised Speech Separation
Open accessAbstract
Formulation of speech separation as a supervised learning problem has shown considerable promise. In its simplest form, a supervised learning algorithm, typically a deep neural network, is trained to learn a mapping from noisy features to a time-frequency representation of the target of interest. Traditionally, the ideal binary mask (IBM) is used as the target because of its simplicity and large speech intelligibility gains. The supervised learning framework, however, is not restricted to the use of binary targets. In this study, we evaluate and compare separation results by using different training targets, including the IBM, the target binary mask, the ideal ratio mask (IRM), the short-time Fourier transform spectral magnitude and its corresponding mask (FFT-MASK), and the Gammatone frequency power spectrum. Our results in various test conditions reveal that the two ratio mask targets, the IRM and the FFT-MASK, outperform the other targets in terms of objective intelligibility and quality metrics. In addition, we find that masking based targets, in general, are significantly better than spectral envelope based targets. We also present comparisons with recent methods in non-negative matrix factorization and speech enhancement, which show clear performance advantages of supervised speech separation.
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
(2010) · Cited by 8,261
Improving neural networks by preventing co-adaptation of feature detectors
Hinton, G. E., Srivastava, N., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. R. (2012) · arXiv · doi:10.48550/arxiv.1207.0580 · Cited by 6,382
Rix, A. W., Beerends, J. G., Hollier, M. P., & Hekstra, A. P. (2002) · 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221) · doi:10.1109/icassp.2001.941023 · Cited by 3,149
TIMIT Acoustic-Phonetic Continuous Speech Corpus
Garofolo, J. S., Lamel, L. F., Fisher, W. M., Pallett, D. S., Dahlgren, N. L., Zue, V. W., & Fiscus, J. G. (2020) · Americanae (AECID Library) · doi:10.35111/17gk-bn40 · Cited by 2,508
An Algorithm for Intelligibility Prediction of Time–Frequency Weighted Noisy Speech
Taal, C. H., Hendriks, R. C., Heusdens, R., & Jensen, J. (2011) · IEEE Transactions on Audio, Speech, and Language Processing · doi:10.1109/tasl.2011.2114881 · Cited by 2,254
Varga, A., & Steeneken, H. J. M. (1993) · Speech Communication · doi:10.1016/0167-6393(93)90095-3 · Cited by 2,105
Speech enhancement theory and practice
Loizou, P. C. (2007) · Cited by 1,823
DARPA TIMIT: acoustic-phonetic continuous speech corpus CD-ROM, NIST speech disc 1-1.1
Garofolo, J. S., Lamel, L. F., Fisher, W. M., Fiscus, J. G., Pallett, D. S., & Dahlgren, N. L. (1993) · doi:10.6028/nist.ir.4930 · Cited by 1,267
An Experimental Study on Speech Enhancement Based on Deep Neural Networks
Xu, Y., Du, J., Dai, L.-R., & Lee, C.-H. (2014) · IEEE Signal Processing Letters · doi:10.1109/lsp.2013.2291240 · Cited by 924
On Ideal Binary Mask As the Computational Goal of Auditory Scene Analysis
Wang, D. (2006) · Speech Separation by Humans and Machines · doi:10.1007/0-387-22794-6_12 · Cited by 556
Self-citationIdeal ratio mask estimation using deep neural networks for robust speech recognition
Narayanan, A., & Wang, D. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6639038 · Cited by 526
Self-citationTowards Scaling Up Classification-Based Speech Separation
Wang, Y., & Wang, D. (2013) · IEEE Transactions on Audio, Speech, and Language Processing · doi:10.1109/tasl.2013.2250961 · Cited by 430
Self-citationSupervised and Unsupervised Speech Enhancement Using Nonnegative Matrix Factorization
Mohammadiha, N., Smaragdis, P., & Leijon, A. (2013) · IEEE Transactions on Audio, Speech, and Language Processing · doi:10.1109/tasl.2013.2270369 · Cited by 389
An algorithm that improves speech intelligibility in noise for normal-hearing listeners
Kim, G., Lu, Y., Hu, Y., & Loizou, P. C. (2009) · The Journal of the Acoustical Society of America · doi:10.1121/1.3184603 · Cited by 321
Binary and ratio time-frequency masks for robust speech recognition
Srinivasan, S., Roman, N., & Wang, D. (2006) · Speech Communication · doi:10.1016/j.specom.2006.09.003 · Cited by 234
Self-citationAn algorithm to improve speech recognition in noise for hearing-impaired listeners
Healy, E. W., Yoho, S. E., Wang, Y., & Wang, D. (2013) · The Journal of the Acoustical Society of America · doi:10.1121/1.4820893 · Cited by 216
Self-citationMVA 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
Speech intelligibility in background noise with ideal binary time-frequency masking
Wang, D., Kjems, U., Pedersen, M. S., Boldt, J. B., & Lunner, T. (2009) · The Journal of the Acoustical Society of America · doi:10.1121/1.3083233 · Cited by 195
Self-citationExploring Monaural Features for Classification-Based Speech Segregation
Wang, Y., Han, K., & Wang, D. (2013) · IEEE Transactions on Audio, Speech, and Language Processing · doi:10.1109/tasl.2012.2221459 · Cited by 183
Self-citationSuper-human multi-talker speech recognition: A graphical modeling approach
Hershey, J. R., Rennie, S. J., Olsen, P. A., & Kristjansson, T. T. (2010) · Computer Speech & Language · doi:10.1016/j.csl.2008.11.001 · Cited by 166
On the optimality of ideal binary time–frequency masks
Li, Y., & Wang, D. (2008) · Speech Communication · doi:10.1016/j.specom.2008.09.001 · Cited by 144
Self-citationKnowledge Matters: Importance of Prior Information for OptimizationPreprint
Gülçehre, Ç., & Bengio, Y. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1301.4083 · Cited by 140
Soft Mask Methods for Single-Channel Speaker Separation
Reddy, A. M., & Raj, B. (2007) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/tasl.2007.901310 · Cited by 124
A Supervised Learning Approach to Monaural Segregation of Reverberant Speech
Jin, Z., & Wang, D. (2009) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/tasl.2008.2010633 · Cited by 102
Self-citationA classification based approach to speech segregation
Han, K., & Wang, D. (2012) · The Journal of the Acoustical Society of America · doi:10.1121/1.4754541 · Cited by 86
Self-citationActive-Set Newton Algorithm for Overcomplete Non-Negative Representations of Audio
Virtanen, T. I., Gemmeke, J. F., & Raj, B. (2013) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/tasl.2013.2263144 · Cited by 66
A Supervised Learning Approach to Monaural Segregation of Reverberant Speech
Jin, Z., & Wang, D. (2007) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2007.367221 · Cited by 47
Self-citationWang, D., & Woodruff, J. (2012) · Cited by 9
Self-citation
Cited by
Conv-TasNet: Surpassing Ideal Time–Frequency Magnitude Masking for Speech Separation
Luo, Y., & Mesgarani, N. (2019) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2019.2915167 · Cited by 2,042
WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing
Chen, S., Wang, C., Chen, Z., Wu, Y., Liu, S., Chen, Z., Li, J., Kanda, N., Yoshioka, T., Xiao, X., et al. (2022) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2022.3188113 · Cited by 1,926
Supervised Speech Separation Based on Deep Learning: An Overview
Wang, D., & Chen, J. (2018) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2018.2842159 · Cited by 1,524
Self-citationA Regression Approach to Speech Enhancement Based on Deep Neural Networks
Xu, Y., Du, J., Dai, L.-R., & Lee, C.-H. (2015) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2014.2364452 · Cited by 1,366
Deep clustering: Discriminative embeddings for segmentation and separation
Hershey, J. R., Chen, Z., Le Roux, J., & Watanabe, S. (2016) · 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2016.7471631 · Cited by 1,354
Metadata
- Authors
- Wang, Y., Narayanan, A., & Wang, D.
- Venue
- IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Published
- 2014-12
- Volume
- 22
- Issue
- 12
- Pages
- 1849-1858
- ISSN
- 2329-9290 (ISSN-L)
- 2329-9304
- OpenAlex
- W2069681747
- Cited by
- 1,067
- References
- 28
- FWCI
- 60.33
- 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.