Joint Learning of Speaker and Phonetic Similarities with Siamese Networks
The DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.
Abstract
Recent work has demonstrated, on small datasets, the feasibility of jointly learning specialized speaker and phone embeddings, in a weakly supervised siamese DNN architecture using word and speaker identity as side information. Here, we scale up these architectures to the 360 hours of the Librispeech corpus by implementing a sampling method to efficiently select pairs of words from the dataset and improving the loss function. We also compare the standard siamese networks fed with same (AA) or different (AB) pairs, to a ’triamese’ network fed with AAB triplets. We use ABX discrimination tasks to evaluate the discriminability and invariance properties of the obtained joined embeddings, and compare these results with mono-embeddings architectures. We find that the joined embeddings architectures succeed in effectively disentangling speaker from phoneme information, with around 10% errors for the matching tasks and embeddings (speaker task on speaker embeddings, and phone task on phone embedding) and near chance for the mismatched task. Furthermore, the results carry over in out-of-domain datasets, even beating the best results obtained with similar weakly supervised techniques.
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
“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
SIGNATURE VERIFICATION USING A “SIAMESE” TIME DELAY NEURAL NETWORK
BROMLEY, J., BENTZ, J. W., BOTTOU, L., GUYON, I., LECUN, Y., MOORE, C., SÄCKINGER, E., & SHAH, R. (1994) · Series in Machine Perception and Artificial Intelligence · doi:10.1142/9789812797926_0003 · Cited by 2,350
Cited by
Siamese Neural Networks: An Overview
Chicco, D. (2021) · Methods in Molecular Biology · doi:10.1007/978-1-0716-0826-5_3 · Cited by 663
Wavesplit: End-to-End Speech Separation by Speaker Clustering
Zeghidour, N., & Grangier, D. (2021) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2021.3099291 · Cited by 257
Self-citationWeakly Supervised Multi-Task Representation Learning for Human Activity Analysis Using Wearables
Sheng, T., & Huber, M. (2020) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3397330 · Cited by 28
Siamese Networks for Weakly Supervised Human Activity Recognition
Sheng, T., & Huber, M. (2019) · 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC) · doi:10.1109/smc.2019.8914045 · Cited by 21
“[17] used a multi-output triamese network to identify the speaker and phonetic similarities jointly.”
MethodSheng, T., & Huber, M. (2025) · Sensors · doi:10.3390/s25134032 · Cited by 5
“Zeghidour et al. [48] leveraged a multi-output Siamese network for speaker and phonetic similarity detection, demonstrating the versatility of this architecture.”
Metadata
- Authors
- Zeghidour, N., Synnaeve, G., Usunier, N., & Dupoux, E.
- Venue
- Interspeech 2016
- Publisher
- ISCA
- Published
- 2016-09-08
- Pages
- 1295-1299
- ISSN
- 2308-457X (ISSN-L)
- OpenAlex
- W2516890051
- Cited by
- 41
- References
- 2
- FWCI
- 3.27
- 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Joint Learning of Speaker and Phonetic Similarities with Siamese Networks. https://app.cochat.ai/papers/10.21437/interspeech.2016-811
- The paper
- Zeghidour, N., Synnaeve, G., Usunier, N., & Dupoux, E. (2016). Joint Learning of Speaker and Phonetic Similarities with Siamese Networks. Interspeech 2016. https://doi.org/10.21437/interspeech.2016-811
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.