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

arXiv: https://arxiv.org/abs/2206.11706 · HTML: https://mlsanity.com/paper/2206.11706/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 34 references that are in the map.
- First posted on arXiv 23 Jun 2022.

## Builds on (most cited first, 15 of 15)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [The Zero Resource Speech Benchmark 2021: Metrics and baselines for unsupervised spoken language modeling](https://mlsanity.com/paper/2011.11588/) (2020)
- [A Comparison of Discrete and Soft Speech Units for Improved Voice Conversion](https://mlsanity.com/paper/2111.02392/) (2021)
- [Vector-quantized neural networks for acoustic unit discovery in the ZeroSpeech 2020 challenge](https://mlsanity.com/paper/2005.09409/) (2020)
- [The Zero Resource Speech Challenge 2020: Discovering discrete subword and word units](https://mlsanity.com/paper/2010.05967/) (2020)
- [The Zero Resource Speech Challenge 2019: TTS without T](https://mlsanity.com/paper/1904.11469/) (2019)
- [Towards unsupervised phone and word segmentation using self-supervised vector-quantized neural networks](https://mlsanity.com/paper/2012.07551/) (2020)
- [Word Segmentation on Discovered Phone Units with Dynamic Programming and Self-Supervised Scoring](https://mlsanity.com/paper/2202.11929/) (2022)
- [Unsupervised acoustic unit discovery for speech synthesis using discrete latent-variable neural networks](https://mlsanity.com/paper/1904.07556/) (2019)
- [Bayesian Subspace Hidden Markov Model for Acoustic Unit Discovery](https://mlsanity.com/paper/1904.03876/) (2019)
- [Graph Coloring: Comparing Cluster Graphs to Factor Graphs](https://mlsanity.com/paper/2110.02048/) (2021)
- [Bayesian Models for Unit Discovery on a Very Low Resource Language](https://mlsanity.com/paper/1802.06053/) (2018)
- [A Probabilistic Graphical Model Approach to the Structure-and-Motion Problem](https://mlsanity.com/paper/2110.03792/) (2021)
- [Incremental Inference on Higher-Order Probabilistic Graphical Models Applied to Constraint Satisfaction Problems](https://mlsanity.com/paper/2202.12916/) (2022)

## Built on by (most cited first, 1 of 1)

- [Towards Learning Discrete Representations via Self-Supervision for Wearables-Based Human Activity Recognition](https://mlsanity.com/paper/2306.01108/) (2023)

## 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.