Pretext Tasks selection for multitask self-supervised speech representation learning

Abstract

Through solving pretext tasks, self-supervised learning leverages unlabeled data to extract useful latent representations replacing traditional input features in the downstream task. In audio/speech signal processing, a wide range of features where engineered through decades of research efforts. As it turns out, learning to predict such features (a.k.a pseudo-labels) has proven to be a particularly relevant pretext task, leading to useful self-supervised representations which prove to be effective for downstream tasks. However, methods and common practices for combining such pretext tasks for better performance on the downstream task have not been explored and understood properly. In fact, the process relies almost exclusively on a computationally heavy experimental procedure, which becomes intractable with the increase of the number of pretext tasks. This paper introduces a method to select a group of pretext tasks among a set of candidates. The method we propose estimates calibrated weights for the partial losses corresponding to the considered pretext tasks during the self-supervised training process. The experiments conducted on automatic speech recognition, speaker and emotion recognition validate our approach, as the groups selected and weighted with our method perform better than classic baselines, thus facilitating the selection and combination of relevant pseudo-labels for self-supervised representation learning.

References in corpus (13)

• Bootstrap your own latent: A new approach to self-supervised Learning
• What Makes for Good Views for Contrastive Learning?
• Big Self-Supervised Models are Strong Semi-Supervised Learners
• Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition
• Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data
• SUPERB: Speech processing Universal PERformance Benchmark
• Predicting What You Already Know Helps: Provable Self-Supervised Learning
• An Unsupervised Autoregressive Model for Speech Representation Learning
• Self-training Improves Pre-training for Natural Language Understanding
• Self-Supervised Learning with Kernel Dependence Maximization
• Speech SIMCLR: Combining Contrastive and Reconstruction Objective for Self-supervised Speech Representation Learning
• Conditional independence for pretext task selection in Self-supervised speech representation learning
• Learning Speech Representations from Raw Audio by Joint Audiovisual Self-Supervision