The DOI matches its Crossref record; 48 of the 48 references it cites were found in a registry or an index.
Speaker-Independent Speech Separation With Deep Attractor Network
Open accessAbstract
Despite the recent success of deep learning for many speech processing tasks, single-microphone, speaker-independent speech separation remains challenging for two main reasons. The first reason is the arbitrary order of the target and masker speakers in the mixture (permutation problem), and the second is the unknown number of speakers in the mixture (output dimension problem). We propose a novel deep learning framework for speech separation that addresses both of these issues. We use a neural network to project the time-frequency representation of the mixture signal into a high-dimensional embedding space. A reference point (attractor) is created in the embedding space to represent each speaker which is defined as the centroid of the speaker in the embedding space. The time-frequency embeddings of each speaker are then forced to cluster around the corresponding attractor point which is used to determine the time-frequency assignment of the speaker. We propose three methods for finding the attractors for each source in the embedding space and compare their advantages and limitations. The objective function for the network is standard signal reconstruction error which enables end-to-end operation during both training and test phases. We evaluated our system using the Wall Street Journal dataset (WSJ0) on two and three speaker mixtures and report comparable or better performance than other state-of-the-art deep learning methods for 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
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
(2014) · Cited by 33,419
(2008) · Journal of Machine Learning Research · Cited by 33,051
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1179 · Cited by 25,545
Distributed Representations of Words and Phrases and their Compositionality
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1310.4546 · Cited by 24,533
Nonlinear Dimensionality Reduction by Locally Linear Embedding
Roweis, S. T., & Saul, L. K. (2000) · Science · doi:10.1126/science.290.5500.2323 · Cited by 14,965
Algorithm AS 136: A K-Means Clustering Algorithm
Hartigan, J. A., & Wong, M. A. (1979) · Applied Statistics · doi:10.2307/2346830 · Cited by 14,523
ALGORITHMS FOR NON-NEGATIVE MATRIX FACTORIZATION
Lee, D. D., & Seung, H. S. (2000) · neural information processing systems · Cited by 9,876
On Spectral Clustering: Analysis and an algorithm
Ng, A. Y., Jordan, M. I., & Weiss, Y. (2001) · Cited by 8,159
Bengio, Y., Louradour, J., Collobert, R., & Weston, J. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553380 · Cited by 5,366 · cited 1×
“During training, we split the input into 100-frame long segments, and then continue training the network with 400-frame long segments, which is known as the curriculum training strategy [25].”
MethodALGORITHMS FOR NON-NEGATIVE MATRIX FACTORIZATION
Seung, D., & Lee, L.-W. (2001) · Cited by 4,753
A Neural Probabilistic Language Model
Bengio, Y., Ducharme, R., Vincent, P., Jauvin, C., Jaz, K., Hofmann, T., Poggio, T., & Shawe-Taylor, J. S. (2000) · Cited by 3,479
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
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
A neural probabilistic language model
BengioYoshua, DucharmeRéjean, VincentPascal, & JanvinChristian (2003) · Journal of Machine Learning Research · doi:10.5555/944919.944966 · Cited by 2,644
Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models
Serban, I., Sordoni, A., Bengio, Y., Courville, A., & Pineau, J. (2016) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v30i1.9883 · Cited by 1,615
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
Self-citationKuhl, P. K. (1991) · Perception & Psychophysics · doi:10.3758/bf03212211 · Cited by 1,331 · cited 1×
“…the well-studied perceptual effects in human speech perception which suggest that the biological neural networks create perceptual attractors (magnets) that warp the acoustic feature space to attract the sounds that are close to them, a phenomenon that is called the Perceptual Magnet Effect [18].”
BackgroundInformational and energetic masking effects in the perception of two simultaneous talkers
Brungart, D. S. (2001) · The Journal of the Acoustical Society of America · doi:10.1121/1.1345696 · Cited by 1,139
Selective cortical representation of attended speaker in multi-talker speech perception
Mesgarani, N., & Chang, E. F. (2012) · Nature · doi:10.1038/nature11020 · Cited by 1,007
Self-citationVirtanen, T. (2007) · IEEE Transactions on Audio, Speech and Language Processing · doi:10.1109/tasl.2006.885253 · Cited by 1,005
Kuhl, P. K., Conboy, B. T., Coffey-Corina, S., Padden, D., Rivera-Gaxiola, M., & Nelson, T. (2008) · Philosophical Transactions of the Royal Society B: Biological Sciences · doi:10.1098/rstb.2007.2154 · Cited by 886
Permutation 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
Speech enhancement based on deep denoising autoencoder
Lu, X., Tsao, Y., Matsuda, S., & Hori, C. (2013) · Interspeech 2013 · doi:10.21437/interspeech.2013-130 · Cited by 834
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
Computational Auditory Scene Analysis: Principles, Algorithms and Applications
Darwin, C. (2008) · The Journal of the Acoustical Society of America · doi:10.1121/1.2920958 · Cited by 749
Phase-sensitive and recognition-boosted speech separation using deep recurrent neural networks
Erdogan, H., Hershey, J. R., Watanabe, S., & Le Roux, J. (2015) · 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2015.7178061 · Cited by 646
The benefit of binaural hearing in a cocktail party: Effect of location and type of interferer
Hawley, M. L., Litovsky, R. Y., & Culling, J. F. (2004) · The Journal of the Acoustical Society of America · doi:10.1121/1.1639908 · Cited by 538
Ideal 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
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
Achieving Human Parity in Conversational Speech Recognition
Xiong, W., Droppo, J., Huang, X., Seide, F. T. B., Seltzer, M., Stolcke, A., Yu, D., & Zweig, G. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1610.05256 · Cited by 451
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 attractor network for single-microphone speaker separation
Chen, Z., Luo, Y., & Mesgarani, N. (2017) · 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2017.7952155 · Cited by 397
Self-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
Blind Source Separation and Independent Component Analysis: A Review
Lee, S.-Y. (2005) · International Conference on Neural Information Processing · Cited by 374
Iverson, P., & Kuhl, P. K. (1995) · The Journal of the Acoustical Society of America · doi:10.1121/1.412280 · Cited by 352
Prediction-driven computational auditory scene analysis
Ellis, D. P. W. (1996) · DSpace@MIT (Massachusetts Institute of Technology) · doi:10.7916/d84j0n13 · Cited by 305
A Tandem Algorithm for Pitch Estimation and Voiced Speech Segregation
Hu, G., & Wang, D. (2010) · IEEE Transactions on Audio, Speech, and Language Processing · doi:10.1109/tasl.2010.2041110 · Cited by 288
Toward Human Parity in Conversational Speech Recognition
Xiong, W., Droppo, J., Huang, X., Seide, F., Seltzer, M. L., Stolcke, A., Yu, D., & Zweig, G. (2017) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2017.2756440 · Cited by 245
Learning Spectral Clustering, With Application To Speech Separation
Bach, F., & Jordan, M. I. (2006) · doi:10.5555/1248547.1248618 · Cited by 245
A Deep Ensemble Learning Method for Monaural Speech Separation
Zhang, X.-L., & Wang, D. (2016) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2016.2536478 · Cited by 219
Time-Frequency Masking in the Complex Domain for Speech Dereverberation and Denoising
Williamson, D. S., & Wang, D. (2017) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2017.2696307 · Cited by 211
Deep clustering and conventional networks for music separation: Stronger together
Luo, Y., Chen, Z., Hershey, J. R., Le Roux, J., & Mesgarani, N. (2017) · 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2017.7952118 · Cited by 168
Self-citationChen, Z., Watanabe, S., Erdoğan, H., & Hershey, J. R. (2015) · Interspeech (USB) · doi:10.21437/interspeech.2015-659 · Cited by 149
Self-citationOn 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
A Regression Approach to Single-Channel Speech Separation Via High-Resolution Deep Neural Networks
Du, J., Tu, Y.-H., Dai, L.-R., & Lee, C. (2016) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2016.2558822 · Cited by 103
Cao, Y., Sridharan, S., & Moody, A. (1997) · IEEE Transactions on Speech and Audio Processing · doi:10.1109/89.568728 · Cited by 29
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
Self-citationSDR – 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
Dual-Path RNN: Efficient Long Sequence Modeling for Time-Domain Single-Channel Speech Separation
Luo, Y., Chen, Z., & Yoshioka, T. (2020) · ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp40776.2020.9054266 · Cited by 780
Self-citationTaSNet: Time-Domain Audio Separation Network for Real-Time, Single-Channel Speech Separation
Luo, Y., & Mesgarani, N. (2018) · 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2018.8462116 · Cited by 686
Self-citationChen, J., Mao, Q., & Liu, D. (2020) · Interspeech 2020 · doi:10.21437/interspeech.2020-2205 · Cited by 320
Metadata
- Authors
- Luo, Y., Chen, Z., & Mesgarani, N.
- Venue
- IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Published
- 2018-04
- Volume
- 26
- Issue
- 4
- Pages
- 787-796
- ISSN
- 2329-9290 (ISSN-L)
- 2329-9304
- OpenAlex
- W2735663686
- Cited by
- 260
- References
- 48
- FWCI
- 28.85
- 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.