Title page for etd-0801114-191423


[Back to Results | New Search]

URN etd-0801114-191423
Author Yu-Hung Huang
Author's Email Address No Public.
Statistics This thesis had been viewed 5537 times. Download 968 times.
Department Computer Science and Engineering
Year 2013
Semester 2
Degree Master
Type of Document
Language zh-TW.Big5 Chinese
Title Noise Robust Speech Recognition using Sparse Representations
Date of Defense 2014-07-24
Page Count 39
Keyword
  • sparse representation
  • noise robustness
  • exemplar dictionary
  • feature enhancement
  • speech recognition
  • Abstract This paper aimed at improving the noise robustness of automatic speech recognition by using a novel technique, called exemplar-based sparse representation. In this paper, we will first describe how to model speech to a linear combination of exemplars. An exemplar is a time-frequency segment from training data, we generate a large amount of exemplars to construct an exemplar dictionary, which is the atoms for the linear combination. After we model the test speech to a linear combination of exemplar dictionary, we can do feature enhancement, directly, or get the posterior probability of frames given phone state by using the coefficients of linear combination together with the exemplars and their phonetic information. Finally, we use the Viterbi search algorithm to get the recognition result. We evaluate the performance by the experiments on AURORA-2 corpus, the results show that although there are no improvement on high SNRs, we can see a huge improvement on low SNRs, we believe that this framework can give us a way for noise robust speech recognition task.
    Advisory Committee
  • Chung-Hsien Wu - chair
  • Hsin-Min Wang - co-chair
  • Chia-Ping Chen - advisor
  • Files
  • etd-0801114-191423.pdf
  • indicate access worldwide
    Date of Submission 2014-09-09

    [Back to Results | New Search]


    Browse | Search All Available ETDs

    If you have more questions or technical problems, please contact eThesys