Unsupervised methods for evaluating speech representations
Author(s)
Gump, Michael H.
Download1192545151-MIT.pdf (2.731Mb)
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
Unsupervised representation learning using deep generative models has produced remarkable results across many domains in recent years. These methods have been applied to speech processing to learn representations useful for downstream supervised tasks like speaker, dialect, or phoneme identification. One research path has been to develop general purpose priors that select effective representations. However, many priors on good representations are difficult to incorporate into unsupervised methods because they are difficult to evaluate without supervision. This thesis proposes to use low-level acoustic features to address this problem for speech. By using techniques in acoustic processing, we develop methods for structured evaluation for speech representations. The evaluation aims both to assess the efficacy of representations for downstream tasks and to validate claims about the priors used to construct them. An evaluation suite for benchmarking and analyzing research in speech representation learning is produced and open-sourced as a result of this thesis.
Description
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, May, 2020 Cataloged from the official PDF of thesis. Includes bibliographical references (pages 47-50).
Date issued
2020Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer SciencePublisher
Massachusetts Institute of Technology
Keywords
Electrical Engineering and Computer Science.