mlsanityData to 7 Oct 2026

A Temporal Extension of Latent Dirichlet Allocation for Unsupervised Acoustic Unit Discovery

arXiv 2206.11706 ↗First posted 23 Jun 2022eess.AS cs.CL cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 15 of its 34 references that are in the map. First posted on arXiv 23 Jun 2022.

Builds on

15 of 34 references.

References · 15

  1. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  2. 2017Neural Discrete Representation Learningcited by 4,650
  3. 2020The Zero Resource Speech Benchmark 2021: Metrics and baselines for unsupervised spoken language modelingcited by 100
  4. 2021A Comparison of Discrete and Soft Speech Units for Improved Voice Conversioncited by 61
  5. 2020Vector-quantized neural networks for acoustic unit discovery in the ZeroSpeech 2020 challengecited by 55
  6. 2020The Zero Resource Speech Challenge 2020: Discovering discrete subword and word unitscited by 39
  7. 2019The Zero Resource Speech Challenge 2019: TTS without Tcited by 38
  8. 2020Towards unsupervised phone and word segmentation using self-supervised vector-quantized neural networkscited by 24
  9. 2022Word Segmentation on Discovered Phone Units with Dynamic Programming and Self-Supervised Scoringcited by 24
  10. 2019Unsupervised acoustic unit discovery for speech synthesis using discrete latent-variable neural networkscited by 20
  11. 2019Bayesian Subspace Hidden Markov Model for Acoustic Unit Discoverycited by 9
  12. 2021Graph Coloring: Comparing Cluster Graphs to Factor Graphscited by 4
3 more
  1. 2018Bayesian Models for Unit Discovery on a Very Low Resource Languagecited by 2
  2. 2021A Probabilistic Graphical Model Approach to the Structure-and-Motion Problemcited by 1
  3. 2022Incremental Inference on Higher-Order Probabilistic Graphical Models Applied to Constraint Satisfaction Problemscited by 1

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.

  1. 2023Towards Learning Discrete Representations via Self-Supervision for Wearables-Based Human Activity Recognitioncited by 7