For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Canonicalization of Feature Parameters for Robust Speech Recognition Based on Distinctive Phonetic Feature (DPF) Vectors
Mohammad NURUL HUDA Muhammad GHULAM Takashi FUKUDA Kouichi KATSURADA Tsuneo NITTA
IEICE TRANSACTIONS on Information and Systems
Publication Date: 2008/03/01
Online ISSN: 1745-1361
Print ISSN: 0916-8532
Type of Manuscript: Special Section PAPER (Special Section on Robust Speech Processing in Realistic Environments)
Category: Feature Extraction
automatic speech recognition, feature extraction, canonicalization, distinctive phonetic feature, hidden factor,
Full Text: PDF(1.8MB)>>
This paper describes a robust automatic speech recognition (ASR) system with less computation. Acoustic models of a hidden Markov model (HMM)-based classifier include various types of hidden factors such as speaker-specific characteristics, coarticulation, and an acoustic environment, etc. If there exists a canonicalization process that can recover the degraded margin of acoustic likelihoods between correct phonemes and other ones caused by hidden factors, the robustness of ASR systems can be improved. In this paper, we introduce a canonicalization method that is composed of multiple distinctive phonetic feature (DPF) extractors corresponding to each hidden factor canonicalization, and a DPF selector which selects an optimum DPF vector as an input of the HMM-based classifier. The proposed method resolves gender factors and speaker variability, and eliminates noise factors by applying the canonicalzation based on the DPF extractors and two-stage Wiener filtering. In the experiment on AURORA-2J, the proposed method provides higher word accuracy under clean training and significant improvement of word accuracy in low signal-to-noise ratio (SNR) under multi-condition training compared to a standard ASR system with mel frequency ceptral coeffient (MFCC) parameters. Moreover, the proposed method requires a reduced, two-fifth, Gaussian mixture components and less memory to achieve accurate ASR.