Unsupervised learning of disentangled representations for speech with neural variational inference models
Author(s)
Hsu, Wei-Ning, Ph. D. Massachusetts Institute of Technology
DownloadFull printable version (14.56Mb)
Other Contributors
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.
Advisor
James R. Glass.
Terms of use
Metadata
Show full item recordAbstract
Despite recent successes in machine learning, artificial intelligence is still far from matching human intelligence in many ways. Two important aspects are transferability and amount of supervision required. Take speech recognition for example: while humans can easily adapt to a new accent without explicit supervision (i.e., ground truth transcripts for speech of a new accent), current machine learning techniques still struggle with such a scenario. We argue that an essential component of human learning is unsupervised or weakly supervised representation learning, which transforms input signals to low dimensional representations that facilitate subsequent structured learning and knowledge acquisition. In this thesis, we develop unsupervised representation learning frameworks for speech data. We start with investigating an existing variational autoencoder (VAE) model for learning latent representations, and derive novel latent space operations for speech transformation. The transformation method is applied to unsupervised domain adaptation problems, which addresses the transferability issues of supervised machine learning framework. We then extend the VAE models, and propose a novel factorized hierarchical variational autoencoder (FHVAE), which better models a generative process of sequential data, and learns not only disentangled, but also interpretable latent representations without any supervision. By leveraging the interpretability, we demonstrate that such representations can be applied to a wide range of tasks, including but not limited to: voice conversion, denoising, speaker verification, speaker invariant phonetic feature extraction, and noise invariant phonetic feature extraction. In the last part of this thesis, we examine scalability issues regarding the original FHVAE training algorithm in terms of runtime, memory, and optimization stability. Based on our analysis, we propose a hierarchical sampling algorithm for training, which enables training of FHVAE models on arbitrarily large datasets.
Description
Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2018. Cataloged from PDF version of thesis. Includes bibliographical references (pages 121-128).
Date issued
2018Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer SciencePublisher
Massachusetts Institute of Technology
Keywords
Electrical Engineering and Computer Science.