2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

Technical Program

Paper Detail

Paper IDMLSP-11.6
Paper Title A Comparison of Discrete Latent Variable Models for Speech Representation Learning
Authors Henry Zhou, University of Toronto, Canada; Alexei Baevski, Michael Auli, Facebook AI Research, United States
SessionMLSP-11: Self-supervised Learning for Speech Processing
LocationGather.Town
Session Time:Tuesday, 08 June, 16:30 - 17:15
Presentation Time:Tuesday, 08 June, 16:30 - 17:15
Presentation Poster
Topic Machine Learning for Signal Processing: [MLR-SSUP] Self-supervised and semi-supervised learning
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Virtual Presentation  Click here to watch in the Virtual Conference
Abstract 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.