A Brief Overview of Unsupervised Neural Speech Representation Learning
arXiv:2203.01829
Abstract
Unsupervised representation learning for speech processing has matured greatly in the last few years. Work in computer vision and natural language processing has paved the way, but speech data offers unique challenges. As a result, methods from other domains rarely translate directly. We review the development of unsupervised representation learning for speech over the last decade. We identify two primary model categories: self-supervised methods and probabilistic latent variable models. We describe the models and develop a comprehensive taxonomy. Finally, we discuss and compare models from the two categories.
arXiv commentThe 2nd Workshop on Self-supervised Learning for Audio and Speech Processing (SAS) at AAAI
References in corpus (29)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Auto-Encoding Variational Bayes
- Representation Learning with Contrastive Predictive Coding
- WaveNet: A Generative Model for Raw Audio
- SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
- Neural Discrete Representation Learning
- Stochastic Backpropagation and Approximate Inference in Deep Generative Models
- Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
- WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing
- The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
- A Recurrent Latent Variable Model for Sequential Data
- Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders
- TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech
- vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations
- An Overview of Deep Semi-Supervised Learning
- Sequential Neural Models with Stochastic Layers
- Deep Contextualized Acoustic Representations For Semi-Supervised Speech Recognition
- Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data
- Improving Transformer-based Speech Recognition Using Unsupervised Pre-training
- Effectiveness of self-supervised pre-training for speech recognition
- DeCoAR 2.0: Deep Contextualized Acoustic Representations with Vector Quantization
- Neural Predictive Coding using Convolutional Neural Networks towards Unsupervised Learning of Speaker Characteristics
- Unsupervised Pre-training of Bidirectional Speech Encoders via Masked Reconstruction
- not-MIWAE: Deep Generative Modelling with Missing not at Random Data
- Contrastive prediction strategies for unsupervised segmentation and categorization of phonemes and words
- Learning Word Embeddings from Speech
- The Zero Resource Speech Challenge 2020: Discovering discrete subword and word units
- Magic dust for cross-lingual adaptation of monolingual wav2vec-2.0
- Variable-rate discrete representation learning