頑健な区間検出とモデル適応に基づく雑音下音声認識  [in Japanese] Noisy Speech Recognition Based on Robust End-point Detection and Model Adaptation  [in Japanese]

Search this Article

Author(s)

Abstract

本論文では、雑音やSNRが時間的に変化する状況に対処することを目的として、頑健な区間検出とモデル適応に基づく雑音下音声認識手法を提案する。入力音声に対し、一定の長さの入力信号を切り出し、その区間に対して木構造から選ばれた最適な雑音適応モデルによって音声認識する。その結果から文区切りを検出し、さらに尤度が最大化するように音素モデルを教師なしで線形変換(MLLR)を行ったのち、再度音声認識を行うことによって認識精度を上げる。日本語対話システムを用いて、二種類の雑音データに対する評価実験により提案手法の有効性を確認した。

How to detect speech periods in noisy speech and how to cope with the temporal variation of noise characteristics are challenging problems. This paper proposes a new robust noisy speech recognition method based on robust end-point detection and online model adaptation using tree-structured noisy speech HMMs. The basic algorithm consists of 1) blind speech segmentation, 2) best matching GMM selection, 3) recognizing the speech with the HMM that corresponds to the GMM, 4) end-point detection based on the recognition results, 5) HMM adaptation based on the recognition results, and 6) re-recognition using the adapted HMM. The processes of 1) through 6) are repeated by shifting the blind segmentation window until the end of the sequence of utterances is detected. The proposed method is evaluated by noisy speech collected by a Japanese dialogue system. Experimental results show that the proposed method is effective in recognizing noisy speech under various noise conditions.

Journal

  • IEICE technical report. Speech

    IEICE technical report. Speech 104(542), 1-6, 2004-12-21

    The Institute of Electronics, Information and Communication Engineers

References:  8

Codes

  • NII Article ID (NAID)
    110003298427
  • NII NACSIS-CAT ID (NCID)
    AN10013221
  • Text Lang
    JPN
  • Article Type
    ART
  • ISSN
    09135685
  • NDL Article ID
    7222319
  • NDL Source Classification
    ZN33(科学技術--電気工学・電気機械工業--電子工学・電気通信)
  • NDL Call No.
    Z16-940
  • Data Source
    CJP  NDL  NII-ELS 
Page Top