Withdraw
Loading…
Dealing with linguistic mismatches for automatic speech recognition
Yang, Xuesong
Loading…
Permalink
https://hdl.handle.net/2142/105187
Description
- Title
- Dealing with linguistic mismatches for automatic speech recognition
- Author(s)
- Yang, Xuesong
- Issue Date
- 2019-04-15
- Director of Research (if dissertation) or Advisor (if thesis)
- Hasegawa-Johnson, Mark
- Doctoral Committee Chair(s)
- Hasegawa-Johnson, Mark
- Committee Member(s)
- Huang, Thomas S.
- Smaragdis, Paris
- Shih, Chilin
- Department of Study
- Graduate College Programs
- Discipline
- Informatics
- Degree Granting Institution
- University of Illinois at Urbana-Champaign
- Degree Name
- Ph.D.
- Degree Level
- Dissertation
- Keyword(s)
- Automatic Speech Recognition
- Acoustic Modeling
- Multi-Accents
- Multi-Lingual
- Acoustic Phonetics
- Distinctive Features
- Acoustic Landmarks
- End-to-End
- Multi-Task Learning
- Model Compression
- Deep Learning
- Pronunciation Error Detection
- Connectionist Temporal Classification
- Abstract
- Recent breakthroughs in automatic speech recognition (ASR) have resulted in a word error rate (WER) on par with human transcribers on the English Switchboard benchmark. However, dealing with linguistic mismatches between the training and testing data is still a significant challenge that remains unsolved. Under the monolingual environment, it is well-known that the performance of ASR systems degrades significantly when presented with the speech from speakers with different accents, dialects, and speaking styles than those encountered during system training. Under the multi-lingual environment, ASR systems trained on a source language achieve even worse performance when tested on another target language because of mismatches in terms of the number of phonemes, lexical ambiguity, and power of phonotactic constraints provided by phone-level n-grams. In order to address the issues of linguistic mismatches for current ASR systems, my dissertation investigates both knowledge-gnostic and knowledge-agnostic solutions. In the first part, classic theories relevant to acoustics and articulatory phonetics that present capability of being transferred across a dialect continuum from local dialects to another standardized language are re-visited. Experiments demonstrate the potentials that acoustic correlates in the vicinity of landmarks could help to build a bridge for dealing with mismatches across difference local or global varieties in a dialect continuum. In the second part, we design an end-to-end acoustic modeling approach based on connectionist temporal classification loss and propose to link the training of acoustics and accent altogether in a manner similar to the learning process in human speech perception. This joint model not only performed well on ASR with multiple accents but also boosted accuracies of accent identification task in comparison to separately-trained models.
- Graduation Semester
- 2019-05
- Type of Resource
- text
- Permalink
- http://hdl.handle.net/2142/105187
- Copyright and License Information
- Copyright 2019 Xuesong Yang
Owning Collections
Graduate Dissertations and Theses at Illinois PRIMARY
Graduate Theses and Dissertations at IllinoisManage Files
Loading…
Edit Collection Membership
Loading…
Edit Metadata
Loading…
Edit Properties
Loading…
Embargoes
Loading…