The DOI matches its Crossref record; 27 of the 27 references it cites were found in a registry or an index.
Deep clustering: Discriminative embeddings for segmentation and separation
Open accessAbstract
We address the problem of "cocktail-party" source separation in a deep learning framework called deep clustering. Previous deep network approaches to separation have shown promising performance in scenarios with a fixed number of sources, each belonging to a distinct signal class, such as speech and noise. However, for arbitrary source classes and number, "class-based" methods are not suitable. Instead, we train a deep network to assign contrastive embedding vectors to each time-frequency region of the spectrogram in order to implicitly predict the segmentation labels of the target spectrogram from the input mixtures. This yields a deep network-based analogue to spectral clustering, in that the embeddings form a low-rank pair-wise affinity matrix that approximates the ideal affinity matrix, while enabling much faster performance. At test time, the clustering step "decodes" the segmentation implicit in the embeddings by optimizing K-means with respect to the unknown assignments. Preliminary experiments on single-channel mixtures from multiple speakers show that a speaker-independent model trained on two-speaker mixtures can improve signal quality for mixtures of held-out speakers by an average of 6dB. More dramatically, the same model does surprisingly well with three-speaker mixtures.
Overview
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
Verification
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.
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
Normalized cuts and image segmentation
Shi, J., & Malik, J. (2000) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.868688 · Cited by 15,502
Hubert, L., & Arabie, P. (1985) · Journal of Classification · doi:10.1007/bf01908075 · Cited by 8,219
Auditory Scene Analysis: The Perceptual Organization of Sound
Bregman, A. S. (1990) · The MIT Press eBooks · doi:10.7551/mitpress/1486.001.0001 · Cited by 3,284
Auditory Scene Analysis: The Perceptual Organization of Sound
Bregman, A. S., & McAdams, S. (1994) · The Journal of the Acoustical Society of America · doi:10.1121/1.408434 · Cited by 3,029
Performance measurement in blind audio source separation
Vincent, E., Gribonval, R., & Fevotte, C. (2006) · IEEE Transactions on Audio, Speech and Language Processing · doi:10.1109/tsa.2005.858005 · Cited by 2,889
Learning Hierarchical Features for Scene Labeling
Farabet, C., Couprie, C., Najman, L., & LeCun, Y. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.231 · Cited by 2,620
Laws of organization in perceptual forms.
Wertheimer, M. (1938) · A source book of Gestalt psychology. · doi:10.1037/11496-005 · Cited by 1,493
Spectral grouping using the nystrom method
Fowlkes, C., Belongie, S., Chung, F., & Malik, J. (2004) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2004.1262185 · Cited by 1,328
On Training Targets for Supervised Speech Separation
Wang, Y., Narayanan, A., & Wang, D. (2014) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2014.2352935 · Cited by 1,067
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
Learning Deep Representations for Graph Clustering
Tian, F., Gao, B., Cui, Q., Chen, E., & Liu, T.-Y. (2014) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v28i1.8916 · Cited by 657
Speech Enhancement with LSTM Recurrent Neural Networks and its Application to Noise-Robust ASR
Weninger, F., Erdogan, H., Watanabe, S., Vincent, E., Le Roux, J., Hershey, J. R., & Schuller, B. (2015) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-22482-4_11 · Cited by 602
Self-citationOn 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
Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation
Huang, P.-S., Kim, M., Hasegawa-Johnson, M., & Smaragdis, P. (2015) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2015.2468583 · Cited by 461
Towards 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
Deep Unfolding: Model-Based Inspiration of Novel Deep Architectures
Hershey, J. R., Roux, J. L., & Weninger, F. (2014) · arXiv · doi:10.48550/arxiv.1409.2574 · Cited by 412 · cited 1×
“s, we expect that further refinement of the model will lead to significant improvement. For example, by combining the clustering step into the embedding BLSTM network using the deep unfolding technique [28], the separation could be jointly trained with embedding and lead to potential better result. Also in this work, th…”
MethodSelf-citationConvolutive 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
Prediction-driven computational auditory scene analysis
Ellis, D. P. W. (1996) · DSpace@MIT (Massachusetts Institute of Technology) · doi:10.7916/d84j0n13 · Cited by 305
Learning Spectral Clustering, With Application To Speech Separation
Bach, F., & Jordan, M. I. (2006) · doi:10.5555/1248547.1248618 · Cited by 245
Deep Embedding Network for Clustering
Huang, P., Huang, Y., Wang, W., & Wang, L. (2014) · 2014 22nd International Conference on Pattern Recognition · doi:10.1109/icpr.2014.272 · Cited by 224
Monaural speech separation and recognition challenge
Cooke, M., Hershey, J. R., & Rennie, S. J. (2010) · Computer Speech & Language · doi:10.1016/j.csl.2009.02.006 · Cited by 197
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
Modelling Auditory Processing and Organisation
Cooke, M. P. (1993) · OpenGrey (Institut de l'Information Scientifique et Technique) · Cited by 172
Super-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
Self-citationSingle-channel speech separation with memory-enhanced recurrent neural networks
Weninger, F. J., Eyben, F., & Schuller, B. W. (2014) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2014.6854294 · Cited by 123
Single-Channel Multitalker Speech Recognition
Rennie, S. J., Hershey, J. R., & Olsen, P. A. (2010) · IEEE Signal Processing Magazine · doi:10.1109/msp.2010.938081 · Cited by 82
Self-citationLocal equivalences of distances between clusterings—a geometric perspective
Meilă, M. (2011) · Machine Learning · doi:10.1007/s10994-011-5267-2 · Cited by 33
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
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
SDR – Half-baked or Well Done?
Roux, J. L., Wisdom, S., Erdogan, H., & Hershey, J. R. (2019) · ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2019.8683855 · Cited by 1,146
Self-citationPermutation invariant training of deep models for speaker-independent multi-talker speech separation
Yu, D., Kolbaek, M., Tan, Z.-H., & Jensen, J. (2017) · 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2017.7952154 · Cited by 839
Kolbaek, M., Yu, D., Tan, Z.-H., & Jensen, J. (2017) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2017.2726762 · Cited by 820
Metadata
- Authors
- Hershey, J. R., Chen, Z., Le Roux, J., & Watanabe, S.
- Venue
- 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- Publisher
- IEEE
- Published
- 2016-03
- Pages
- 31-35
- ISSN
- 1520-6149 (ISSN-L)
- OpenAlex
- W2221409856
- Cited by
- 1,354
- References
- 27
- FWCI
- 96.72
- Type
- conference paper
- 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.