Noise-Robust ASR for the third 'CHiME' Challenge Exploiting Time-Frequency Masking based Multi-Channel Speech Enhancement and Recurrent Neural Network
This addresses speech recognition in noisy environments for practical applications, though it is incremental as it integrates existing methods.
The paper presents a noise-robust automatic speech recognition system for the CHiME challenge that combines multi-channel speech enhancement with advanced neural network techniques, achieving over 57% relative reduction in word error rate compared to the best baseline on real-data tests.
In this paper, the Lingban entry to the third 'CHiME' speech separation and recognition challenge is presented. A time-frequency masking based speech enhancement front-end is proposed to suppress the environmental noise utilizing multi-channel coherence and spatial cues. The state-of-the-art speech recognition techniques, namely recurrent neural network based acoustic and language modeling, state space minimum Bayes risk based discriminative acoustic modeling, and i-vector based acoustic condition modeling, are carefully integrated into the speech recognition back-end. To further improve the system performance by fully exploiting the advantages of different technologies, the final recognition results are obtained by lattice combination and rescoring. Evaluations carried out on the official dataset prove the effectiveness of the proposed systems. Comparing with the best baseline result, the proposed system obtains consistent improvements with over 57% relative word error rate reduction on the real-data test set.