The DOI matches its Crossref record; 20 of the 20 references it cites were found in a registry or an index.
Discriminatively trained recurrent neural networks for single-channel speech separation
Abstract
This paper describes an in-depth investigation of training criteria, network architectures and feature representations for regression-based single-channel speech separation with deep neural networks (DNNs). We use a generic discriminative training criterion corresponding to optimal source reconstruction from time-frequency masks, and introduce its application to speech separation in a reduced feature space (Mel domain). A comparative evaluation of time-frequency mask estimation by DNNs, recurrent DNNs and non-negative matrix factorization on the 2nd CHiME Speech Separation and Recognition Challenge shows consistent improvements by discriminative training, whereas long short-term memory recurrent DNNs obtain the overall best results. Furthermore, our results confirm the importance of fine-tuning the feature representation for DNN training.
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
Speech recognition with deep recurrent neural networks
Graves, A., Mohamed, A.-R., & Hinton, G. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6638947 · Cited by 8,893 · cited 2×
“The combination of deep structures with temporal recurrence yields so-called deep recurrent neural networks (DRNNs) [13].”
BackgroundLearning long-term dependencies with gradient descent is difficult
Bengio, Y., Simard, P., & Frasconi, P. (1994) · IEEE Transactions on Neural Networks · doi:10.1109/72.279181 · Cited by 8,542 · cited 1×
“However, this approach (‘backpropagation through time’) suffers from a vanishing or exploding gradient for larger T , making the optimization difficult [16].”
BackgroundLearning to forget: Continual prediction with LSTM
Gers, F. A., Schmidhuber, J., & Cummins, F. (2000) · Neural Computation · doi:10.1162/089976600300015015 · Cited by 4,823
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
Towards End-To-End Speech Recognition with Recurrent Neural Networks
Graves, A., & Jaitly, N. (2014) · Cited by 2,557
Perceptual linear predictive (PLP) analysis of speech
Hermansky, H. (1990) · The Journal of the Acoustical Society of America · doi:10.1121/1.399423 · Cited by 2,536
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
Boulanger-Lewandowski, N., Bengio, Y., & Vincent, P. (2012) · arXiv (Cornell University) · doi:10.48550/arxiv.1206.6392 · Cited by 459
Deep learning for monaural speech separation
Huang, P.-S., Kim, M., Hasegawa-Johnson, M., & Smaragdis, P. (2014) · 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2014.6853860 · Cited by 423
Cited by
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-citationPhase-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
Self-citationSpeech 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-citationReal Time Speech Enhancement in the Waveform Domain
Défossez, A., Synnaeve, G., & Adi, Y. (2020) · Interspeech 2020 · doi:10.21437/interspeech.2020-2409 · Cited by 537
Investigating RNN-based speech enhancement methods for noise-robust Text-to-Speech
Valentini-Botinhao, C., Wang, X., Takaki, S., & Yamagishi, J. (2016) · 9th ISCA Workshop on Speech Synthesis Workshop (SSW 9) · doi:10.21437/ssw.2016-24 · Cited by 463
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
Light Gated Recurrent Units for Speech Recognition
Ravanelli, M., Brakel, P., Omologo, M., & Bengio, Y. (2018) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2017.2762739 · Cited by 411
Tan, K., & Wang, D. (2020) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2019.2955276 · Cited by 348
WHAM!: Extending Speech Separation to Noisy Environments
Wichern, G., Antognini, J., Flynn, M., Zhu, L. R., McQuinn, E., Crow, D., Manilow, E., & Roux, J. L. (2019) · Interspeech 2019 · doi:10.21437/interspeech.2019-2821 · Cited by 338
An Overview of Deep-Learning-Based Audio-Visual Speech Enhancement and Separation
Michelsanti, D., Tan, Z.-H., Zhang, S.-X., Xu, Y., Yu, M., Yu, D., & Jensen, J. (2021) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2021.3066303 · Cited by 316
Fu, S.-W., Wang, T.-W., Tsao, Y., Lu, X., & Kawai, H. (2018) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2018.2821903 · Cited by 314
Deep Learning for Environmentally Robust Speech Recognition: An Overview of Recent Developments
Zhang, Z., Geiger, J., Pohjalainen, J., Mousa, A. E.-D., Jin, W., & Schuller, B. (2018) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3178115 · Cited by 313
Self-citationMultichannel Audio Source Separation With Deep Neural Networks
Nugraha, A. A., Liutkus, A., & Vincent, E. (2016) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2016.2580946 · Cited by 300
TinyLSTMs: Efficient Neural Speech Enhancement for Hearing Aids
Fedorov, I., Stamenovic, M., Jensen, C., Yang, L.-C., Mandell, A., Gan, Y., Mattina, M., & Whatmough, P. N. (2020) · Interspeech 2020 · doi:10.21437/interspeech.2020-1864 · Cited by 116
“70dB SDR on the test set (Table 3), which is comparable to [34, 20].”
Result
Metadata
- Authors
- Weninger, F., Hershey, J. R., Le Roux, J., & Schuller, B.
- Venue
- 2014 IEEE Global Conference on Signal and Information Processing (GlobalSIP)
- Publisher
- IEEE
- Published
- 2014-12
- Pages
- 577-581
- ISSN
- 2376-4066 (ISSN-L)
- OpenAlex
- W2046869671
- Cited by
- 283
- References
- 20
- FWCI
- 19.86
- Type
- conference paper
- Language
- en
- Open access
- closed
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.