An Unsupervised Autoregressive Model for Speech Representation Learning

Abstract

This paper proposes a novel unsupervised autoregressive neural model for learning generic speech representations. In contrast to other speech representation learning methods that aim to remove noise or speaker variabilities, ours is designed to preserve information for a wide range of downstream tasks. In addition, the proposed model does not require any phonetic or word boundary labels, allowing the model to benefit from large quantities of unlabeled data. Speech representations learned by our model significantly improve performance on both phone classification and speaker verification over the surface features and other supervised and unsupervised approaches. Further analysis shows that different levels of speech information are captured by our model at different layers. In particular, the lower layers tend to be more discriminative for speakers, while the upper layers provide more phonetic content.

Accepted to Interspeech 2019. Code available at: https://github.com/iamyuanchung/Autoregressive-Predictive-Coding

References in corpus (3)

• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• The information bottleneck method
• Discriminative Acoustic Word Embeddings: Recurrent Neural Network-Based Approaches

Cited by in corpus (16)

• Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition
• BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition
• Unsupervised Automatic Speech Recognition: A Review
• Deep Representation Learning in Speech Processing: Challenges, Recent Advances, and Future Trends
• Discrete and continuous representations and processing in deep learning: Looking forward
• Towards Transfer Learning for End-to-End Speech Synthesis from Deep Pre-Trained Language Models
• CSTNet: Contrastive Speech Translation Network for Self-Supervised Speech Representation Learning
• Transformer based unsupervised pre-training for acoustic representation learning
• Towards Semi-Supervised Semantics Understanding from Speech
• Semi-Supervised Spoken Language Understanding via Self-Supervised Speech and Language Model Pretraining
• Learning Speech Representations from Raw Audio by Joint Audiovisual Self-Supervision
• Comparison of Self-Supervised Speech Pre-Training Methods on Flemish Dutch
• Two-stage Textual Knowledge Distillation for End-to-End Spoken Language Understanding
• Unsupervised Speech Representation Learning for Behavior Modeling using Triplet Enhanced Contextualized Networks
• Deep generative factorization for speech signal
• Pretext Tasks selection for multitask self-supervised speech representation learning