# A Comparison of Discrete Latent Variable Models for Speech Representation Learning

arXiv: https://arxiv.org/abs/2010.14230 · HTML: https://mlsanity.com/paper/2010.14230/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Oct 2020.

## Built on by (most cited first, 8 of 8)

- [Self-Supervised Speech Representation Learning: A Review](https://mlsanity.com/paper/2205.10643/) (2022)
- [Autoregressive Co-Training for Learning Discrete Speech Representations](https://mlsanity.com/paper/2203.15840/) (2022)
- [Latent-Domain Predictive Neural Speech Coding](https://mlsanity.com/paper/2207.08363/) (2022)
- [ATCSpeechNet: A multilingual end-to-end speech recognition framework for air traffic control systems](https://mlsanity.com/paper/2102.08535/) (2021)
- [DSE-TTS: Dual Speaker Embedding for Cross-Lingual Text-to-Speech](https://mlsanity.com/paper/2306.14145/) (2023)
- [Learning Dependencies of Discrete Speech Representations with Neural Hidden Markov Models](https://mlsanity.com/paper/2210.16659/) (2022)
- [Vector Quantized-Elites: Unsupervised and Problem-Agnostic Quality-Diversity Optimization](https://mlsanity.com/paper/2504.08057/) (2025)
- [Learning Invariant Representation and Risk Minimized for Unsupervised Accent Domain Adaptation](https://mlsanity.com/paper/2210.08182/) (2022)

## Abstract (arXiv)

Neural latent variable models enable the discovery of interesting structure in speech audio data. This paper presents a comparison of two different approaches which are broadly based on predicting future time-steps or auto-encoding the input signal. Our study compares the representations learned by vq-vae and vq-wav2vec in terms of sub-word unit discovery and phoneme recognition performance. Results show that future time-step prediction with vq-wav2vec achieves better performance. The best system achieves an error rate of 13.22 on the ZeroSpeech 2019 ABX phoneme discrimination challenge