Back to Search
Start Over
A noise-robust feature extraction method based on pitch-synchronous ZCPA for ASR
- Source :
- INTERSPEECH
- Publication Year :
- 2004
- Publisher :
- ISCA, 2004.
-
Abstract
- In this paper, we propose a novel feature extraction method based on an auditory nervous system for robust automatic speech recognition (ASR). In the proposed method, a pitchsynchronous mechanism is embedded in ZCPA (ZeroCrossings Peak-Amplitudes), which has previously been shown to outperform the conventional features in the presence of noise. A noise-robust non-delayed pitch determination algorithm (PDA) is also developed. In the experiment, the proposed pitch-synchronous ZCPA (PS-ZCPA) was proved more robust than the original ZCPA method. Moreover, a simple noise subtraction (NS) method is also integrated in the proposed method and the performance was evaluated using the Aurora-2J database. The experimental results showed the superiority of the proposed PS-ZCPA method with NS over the PS-ZCPA method without NS.
Details
- Database :
- OpenAIRE
- Journal :
- Interspeech 2004
- Accession number :
- edsair.doi...........ce1ec2db5ec68e8084d9f5fc9fb36967