The search functionality is under construction.
The search functionality is under construction.

Author Search Result

[Author] Yuzo HAMANAKA(1hit)

1-1hit
  • Committee-Based Active Learning for Speech Recognition

    Yuzo HAMANAKA  Koichi SHINODA  Takuya TSUTAOKA  Sadaoki FURUI  Tadashi EMORI  Takafumi KOSHINAKA  

     
    PAPER-Speech and Hearing

      Vol:
    E94-D No:10
      Page(s):
    2015-2023

    We propose a committee-based method of active learning for large vocabulary continuous speech recognition. Multiple recognizers are trained in this approach, and the recognition results obtained from these are used for selecting utterances. Those utterances whose recognition results differ the most among recognizers are selected and transcribed. Progressive alignment and voting entropy are used to measure the degree of disagreement among recognizers on the recognition result. Our method was evaluated by using 191-hour speech data in the Corpus of Spontaneous Japanese. It proved to be significantly better than random selection. It only required 63 h of data to achieve a word accuracy of 74%, while standard training (i.e., random selection) required 103 h of data. It also proved to be significantly better than conventional uncertainty sampling using word posterior probabilities.