A Study of Inductive Biases for Unsupervised Speech Representation Learning

Distributed representations, or embeddings, are commonly learned without supervision on very large unannotated corpora for natural language processing. In speech processing, deep network-based representations such as bottlenecks and x-vectors have had some success,but are limited to supervised or partly supervised settings where annotations are available and are not optimized to separate underlying factors. Here, we propose a generative model with deep encoders and decoders that can learn interpretable speech representations without supervision. Our inductive biases operate as prior distributions in a variational autoencoder model and allow us to separate several latent variables along a continuous range of time-scale properties, as opposed to binary oppositions or hierarchical factorization that have been previously proposed. On simulated data, we confirm that these biases enable the model to accurately recover phonetic and speaker underlying factors. On TIMIT and LibriSpeech, they yield representations that separate phonetic and speaker information, as evidenced by unsupervised results on downstream phoneme and speaker classification tasks using a simple k-means classifier.