Reducing Computation Time of the Rapid Unsupervised Speaker Adaptation based on HMM-Sufficient Statistics

• Gomez, Randy

• Toda, Tomoki

• Saruwatari, Hiroshi

• Shikano, Kiyohiro

抄録

In real-time speech recognition applications, there is a need to implement a fast and reliable adaptation algorithm. We propose a method to reduce adaptation time of the rapid unsupervised speaker adaptation based on HMM-Sufficient Statistics. We use only a single arbitrary utterance without transcriptions in selecting the N-best speakers' Sufficient Statistics created offline to provide data for adaptation to a target speaker. Further reduction of N-best implies a reduction in adaptation time. However, it degrades recognition performance due to insufficiency of data needed to robustly adapt the model. Linear interpolation of the global HMM-Sufficient Statistics offsets this negative effect and achieves a 50% reduction in adaptation time without compromising the recognition performance. Furthermore, we compared our method with Vocal Tract Length Normalization (VTLN), Maximum A Posteriori (MAP) and Maximum Likelihood Linear Regression (MLLR). Moreover, we tested in office, car, crowd and booth noise environments in 10dB, 15dB, 20dB and 25dB SNRs.

収録刊行物

• IEICE Transactions on Information and Systems

  IEICE Transactions on Information and Systems E90-D (2), 554-561, 2007-02

  電子情報通信学会

キーワード

• HMM-sufficient statistics
• unsupervised
• rapid adaptation
• speech recognition

詳細情報

• CRID: 1050577309353406336
• NII論文ID: 110007519501
• NII書誌ID: AA10826272
• ISSN: 09168532
• HANDLE: 10061/7823
• Web Site: https://naist.repo.nii.ac.jp/records/3831
• 本文言語コード: en
• 資料種別: journal article
• データソース種別:
  • IRDB
  • CiNii Articles