A Temporal Extension of Latent Dirichlet Allocation for Unsupervised Acoustic Unit Discovery
Open accessThe DOI matches its Crossref record; 35 of the 35 references it cites were found in a registry or an index.
Abstract
Latent Dirichlet allocation (LDA) is widely used for unsupervised topic modelling on sets of documents.No temporal information is used in the model.However, there is often a relationship between the corresponding topics of consecutive tokens.In this paper, we present an extension to LDA that uses a Markov chain to model temporal information.We use this new model for acoustic unit discovery from speech.As input tokens, the model takes a discretised encoding of speech from a vector quantised (VQ) neural network with 512 codes.The goal is then to map these 512 VQ codes to 50 phone-like units (topics) in order to more closely resemble true phones.In contrast to the base LDA, which only considers how VQ codes co-occur within utterances (documents), the Markov chain LDA additionally captures how consecutive codes follow one another.This extension leads to an increase in cluster quality and phone segmentation results compared to the base LDA.Compared to a recent vector quantised neural network approach that also learns 50 units, the extended LDA model performs better in phone segmentation but worse in mutual information.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Interestingly, the discrete representations enable the unsupervised discovery of acoustic units where phonemes are automatically mapped to a small set of discrete representations, enabling phoneme discovery and segmentation [54,55,56,57].”
From Towards Learning Discrete Representations via Self-Supervision for Wearables-Based Human Activity Recognition (2024) · cites this paper as [54]
Citations
Cites
On Information and Sufficiency
Kullback, S., & Leibler, R. A. (1951) · The Annals of Mathematical Statistics · doi:10.1214/aoms/1177729694 · Cited by 20,193
Introduction to information retrieval
(2009) · Choice Reviews Online · doi:10.5860/choice.46-2715 · Cited by 12,278
Blei, D. M., Ng, A. Y., & Jordan, M. I. (2002) · Advances in Neural Information Processing Systems 14 · doi:10.7551/mitpress/1120.003.0082 · Cited by 12,223
Pattern Recognition and Machine Learning
(2006) · doi:10.1007/978-0-387-45528-0 · Cited by 9,824
(2006) · Springer eBooks · Cited by 8,123
Koller, D., & Friedman, N. (2009) · The MIT Press eBooks · Cited by 7,555
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
(2009) · Cited by 6,153
Lauritzen, S. L., & Spiegelhalter, D. J. (1988) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1988.tb01721.x · Cited by 3,902
Neural Discrete Representation Learning
Oord, A. V. D., Vinyals, O., & Kavukcuoglu, K. (2017) · arXiv · doi:10.48550/arxiv.1711.00937 · Cited by 2,729
Bayesian Reasoning and Machine Learning
Barber, D. (2012) · Cambridge University Press eBooks · doi:10.1017/cbo9780511804779 · Cited by 1,631
Automatic speech recognition for under-resourced languages: A survey
Besacier, L., Barnard, E., Karpov, A., & Schultz, T. (2014) · Speech Communication · doi:10.1016/j.specom.2013.07.008 · Cited by 482
Pitt, M. A., Johnson, K., Hume, E., Kiesling, S., & Raymond, W. (2005) · Speech Communication · doi:10.1016/j.specom.2004.09.001 · Cited by 390
A Nonparametric Bayesian Approach to Acoustic Model Discovery
Lee, C.-Y., & Glass, J. R. (2012) · Cited by 208
A Comparison of Discrete and Soft Speech Units for Improved Voice Conversion
van Niekerk, B., Carbonneau, M., Zaïdi, J., Baas, M., Seuté, H., & Kamper, H. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9746484 · Cited by 189
Self-citationShafer, G. R., & Shenoy, P. P. (1990) · Annals of Mathematics and Artificial Intelligence · doi:10.1007/bf01531015 · Cited by 179
Vector-Quantized Neural Networks for Acoustic Unit Discovery in the ZeroSpeech 2020 Challenge
Niekerk, B. V., Nortje, L., & Kamper, H. (2020) · Interspeech 2020 · doi:10.21437/interspeech.2020-1693 · Cited by 114
Self-citationThe Zero Resource Speech Challenge 2019: TTS Without T
Dunbar, E., Algayres, R., Karadayi, J., Bernard, M., Benjumea, J., Cao, X.-N., Miskic, L., Dugrain, C., Ondel, L., Black, A. W., et al. (2019) · Interspeech 2019 · doi:10.21437/interspeech.2019-2904 · Cited by 93
Variational Inference for Acoustic Unit Discovery
Ondel, L., Burget, L., & Černocký, J. (2016) · Procedia Computer Science · doi:10.1016/j.procs.2016.04.033 · Cited by 91
Breaking the Unwritten Language Barrier: The BULB Project
Adda, G., Stüker, S., Adda‐Decker, M., Ambouroue, O., Besacier, L., Blachon, D., Bonneau-Maynard, H., Godard, P., Hamlaoui, F., Idiatov, D., et al. (2016) · Procedia Computer Science · doi:10.1016/j.procs.2016.04.023 · Cited by 86
An improved speech segmentation quality measure: the r-value
Räsänen, O. J., Laine, U. K., & Altosaar, T. (2009) · Interspeech (USB) · doi:10.21437/interspeech.2009-538 · Cited by 81
Nguyen, T. A., de Seyssel, M., Rozé, P., Rivière, M., Kharitonov, E., Baevski, A., Dunbar, E., & Emmanuel Dupoux, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.11588 · Cited by 58
Heck, M., Sakti, S., & Nakamura, S. (2017) · 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) · doi:10.1109/asru.2017.8269011 · Cited by 54
Eloff, R., Nortje, A., Niekerk, B. V., Govender, A., Nortje, L., Pretorius, A., Biljon, E. V., Westhuizen, E. V. D., Staden, L. V., & Kamper, H. (2019) · Interspeech 2019 · doi:10.21437/interspeech.2019-1518 · Cited by 52
Self-citationKamper, H., & van Niekerk, B. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-50 · Cited by 47
Self-citationHidden Markov Model Variational Autoencoder for Acoustic Unit Discovery
Ebbers, J., Heymann, J., Drude, L., Glarner, T., Haeb-Umbach, R., & Raj, B. (2017) · Interspeech 2017 · doi:10.21437/interspeech.2017-1160 · Cited by 45
Word Segmentation on Discovered Phone Units With Dynamic Programming and Self-Supervised Scoring
Kamper, H. (2023) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2022.3229264 · Cited by 24
Self-citationThe Zero Resource Speech Challenge 2020: Discovering discrete subword and word unitsPreprint
Dunbar, E., Karadayi, J., Bernard, M., Cao, X.-N., Algayres, R., Ondel, L., Besacier, L., Sakti, S., & Emmanuel Dupoux, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.05967 · Cited by 22
Bayesian Subspace Hidden Markov Model for Acoustic Unit Discovery
Ondel, L., Vydana, H. K., Burget, L., & Černocký, J. (2019) · Interspeech (USB) · doi:10.21437/interspeech.2019-2224 · Cited by 21
Bayesian Models for Unit Discovery on a Very Low Resource Language
Ondel, L., Godard, P., Besacier, L., Larsen, E., Hasegawa‐Johnson, M., Scharenborg, O., Emmanuel Dupoux, A., Burget, L., Yvon, F., & Khudanpur, S. P. (2018) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2018.8461545 · Cited by 20
Learning Supervised Feature Transformations on Zero Resources for Improved Acoustic Unit Discovery
Heck, M. C., Sakti, S., & Nakamura, S. (2017) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2017edp7175 · Cited by 11
Bayesian phonotactic Language Model for Acoustic Unit Discovery
Ondel, L., Burget, L., Černocký, J., & Kesiraju, S. (2017) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2017.7953258 · Cited by 10
A probabilistic graphical model approach to the structure-and-motion problem
Streicher, S., Brink, W., & du Preez, J. A. (2016) · Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA) · doi:10.1109/robomech.2016.7813137 · Cited by 3
Takahashi, S., Sakti, S., & Nakamura, S. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-1340 · Cited by 2
Streicher, S. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2202.12916 · Cited by 2
Cited by
Haresamudram, H., Essa, I., & Plötz, T. (2024) · Sensors · doi:10.3390/s24041238 · Cited by 14
Automatic Topic Classification And Document Clustering Using Lda Based Machine Learning Techniques
Yuvaraj, K., Setia, N., Sangeetha, S., Goyal, P., Thomas, P. K., & Meshram, V. A. (2024) · Global Conference on Communications and Information Technologies (GCCIT) · doi:10.1109/gccit63234.2024.10862470
Amzil, T., Jannani, A., Abdelouahid, R. A., & Sael, N. (2026) · International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET) · doi:10.1109/iraset68627.2026.11538461
Metadata
- Authors
- van der Merwe, W., Kamper, H., & Adam du Preez, J.
- Affiliations
- Stellenbosch University (ZA)
- ORCID
- Kamper, Herman
- Venue
- Interspeech 2022
- Publisher
- ISCA
- Published
- 2022-09-18
- Pages
- 1426-1430
- ISSN
- 2308-457X (ISSN-L)
- OpenAlex
- W4297841546
- Cited by
- 3
- References
- 34
- Citations by year
- 2026: 1 · 2024: 2
- FWCI
- 0.28
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- cc-by-sa
- Locations
- Interspeech (USB) (publishedVersion)
- arXiv (Cornell University) (submittedVersion, cc-by-sa)
- arXiv (Cornell University)
- Funders
- National Research Foundation
- Center for High Performance Computing
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Keywords
- latent Dirichlet allocation, Markov chains, phone segmentation, speech representation, topic modeling, mutual information
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.