원문정보
초록
영어
The noisy short utterance is polluted by noise and corpus is less, so the recognition rate significantly decreased. For improving recognition rate, we proposed the dual information quality discrimination algorithm to classify the speech frames: one is differences detection and discrimination algorithm (DDADA), another is the improved SNR discrimination algorithm (ISNRDA). Based on the above two algorithms, the speech frames are classified to three classes: high quality, medium quality and low quality. We proposed GMM-UBM three-stage classification model, and we combine the dual information quality discrimination algorithm with GMM-UBM three-stage classification model. Experiments show that, the dual discrimination quality algorithms can be more precise to classify speech frame, and combining it with GMM-UBM three-stage classification model can make full use of limited corpus of short utterance and can improve the speaker recognition rate of the noisy short utterance.
목차
1. Introduction
2. Speech Frames Quality Discrimination
2.1 Extract Spectral Feature of Noisy Speech
2.2 NMF-SNRDA(Nonnegative Matrix Factorization-SNR Discrimination Algorithm)
2.3 Differences Detection and Discrimination Algorithm (DDADA)
3. GMM-UBM Three-stage Classification Model
3.2 Differences Detection and Discrimination Algorithm (DDADA)
4. GMM-UBM Three-stage Classification Model
5. Experiments and Results
5.1 Speech Database and Noise
5.2 The Relationship between Classification Methods and Recognition Rate
5.3 Research on the Dual Information Quality Discrimination Algorithm
6. Conclusion
References