Learning Speaker Representations with Mutual Information
Open accessThe DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
Abstract
Learning good representations is of crucial importance in deep learning. Mutual Information (MI) or similar measures of statistical dependence are promising tools for learning these representations in an unsupervised way. Even though the mutual information between two random variables is hard to measure directly in high dimensional spaces, some recent studies have shown that an implicit optimization of MI can be achieved with an encoder-discriminator architecture similar to that of Generative Adversarial Networks (GANs). In this work, we learn representations that capture speaker identities by maximizing the mutual information between the encoded representations of chunks of speech randomly sampled from the same sentence. The proposed encoder relies on the SincNet architecture and transforms raw speech waveform into a compact feature vector. The discriminator is fed by either positive samples (of the joint distribution of encoded chunks) or negative samples (from the product of the marginals) and is trained to separate them. We report experiments showing that this approach effectively learns useful speaker representations, leading to promising results on speaker identification and verification tasks. Our experiments consider both unsupervised and semi-supervised settings and compare the performance achieved with different objective functions.
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
FaceNet: A unified embedding for face recognition and clustering
Schroff, F., Kalenichenko, D., & Philbin, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298682 · Cited by 15,267
Representation Learning with Contrastive Predictive Coding
Oord, A. V. D., Li, Y., & Vinyals, O. (2018) · arXiv · doi:10.48550/arxiv.1807.03748 · Cited by 6,242
“Librispeech: an ASR corpus based on public domain audio books,”
Panayotov, V., Chen, G., Povey, D., & Khudanpur, S. (2015) · 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2015.7178964 · Cited by 6,072
Greedy layer-wise training of deep networks
Bengio, Y., Lamblin, P., Popovici, D., & Larochelle, H. (2007) · Advances in Neural Information Processing Systems 19 · doi:10.7551/mitpress/7503.003.0024 · Cited by 4,841
Self-citationContext-dependent pre-trained deep neural networks for large-vocabulary speech recognition
Dahl, G. E., Yu, D., Deng, L., & Acero, A. (2012) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/tasl.2011.2134090 · Cited by 3,011
VoxCeleb: A Large-Scale Speaker Identification Dataset
Nagrani, A., Chung, J. S., & Zisserman, A. (2017) · Interspeech 2017 · doi:10.21437/interspeech.2017-950 · Cited by 2,210
Estimation of entropy and mutual information
Paninski, L. (2003) · Neural Computation · doi:10.1162/089976603321780272 · Cited by 1,442
Adieu features? End-to-end speech emotion recognition using a deep convolutional recurrent network
Trigeorgis, G., Ringeval, F., Brueckner, R., Marchi, E., Nicolaou, M. A., Schuller, B., & Zafeiriou, S. (2016) · 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2016.7472669 · Cited by 904
Speaker Recognition from Raw Waveform with SincNet
Ravanelli, M., & Bengio, Y. (2018) · 2018 IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt.2018.8639585 · Cited by 896
Self-citationMaximum mutual information estimation of hidden Markov model parameters for speech recognition
Bahl, L., Brown, P., de Souza, P., & Mercer, R. (2005) · ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing · doi:10.1109/icassp.1986.1169179 · Cited by 817
Cited by
wav2vec: Unsupervised Pre-Training for Speech Recognition
Schneider, S., Baevski, A., Collobert, R., & Auli, M. (2019) · Interspeech 2019 · doi:10.21437/interspeech.2019-1873 · Cited by 1,290
End-to-End anti-spoofing with RawNet2
Tak, H., Patino, J., Todisco, M., Nautsch, A., Evans, N., & Larcher, A. (2021) · ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp39728.2021.9414234 · Cited by 402
Self-supervised speech representation learning: A review
Mohamed, A., Lee, H.-Y., Borgholt, L., Havtorn, J. D., Edin, J., Igel, C., Kirchhoff, K., Li, S.-W., Livescu, K., Maaløe, L., et al. (2022) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2022.3207050 · Cited by 372
“ConvDMM [235] LS 50 [234]/360/ 960 hrs PC/PR WSJ si284 WSJ eval92 X 5(12)/50(12)/100(12) mins, 4(12)/8(12)/40(12) hrs”
BackgroundInfluentialUnsupervised Attributed Multiplex Network Embedding
Park, C., Kim, D., Han, J., & Yu, H. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i04.5985 · Cited by 286
Multi-Task Self-Supervised Learning for Robust Speech Recognition
Ravanelli, M., Zhong, J., Pascual, S., Swietojanski, P., Monteiro, J., Trmal, J., & Bengio, Y. (2020) · ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp40776.2020.9053569 · Cited by 258
Self-citation
Metadata
- Authors
- Ravanelli, M., & Bengio, Y.
- Venue
- Interspeech 2019
- Publisher
- ISCA
- Published
- 2019-09-15
- Pages
- 1153-1157
- ISSN
- 2308-457X (ISSN-L)
- OpenAlex
- W2902368158
- Cited by
- 96
- References
- 11
- FWCI
- 7.71
- 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Learning Speaker Representations with Mutual Information. https://app.cochat.ai/papers/10.21437/interspeech.2019-2380
- The paper
- Ravanelli, M., & Bengio, Y. (2019). Learning Speaker Representations with Mutual Information. Interspeech 2019. https://doi.org/10.21437/interspeech.2019-2380
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.