Noise robust ASR in reverberated multisource environments applying convolutive NMF and Long Short-Term Memory

This article proposes and evaluates various methods to integrate the concept of bidirectional Long Short-Term Memory (BLSTM) temporal context modeling into a system for automatic speech recognition (ASR) in noisy and reverberated environments. Building on recent advances in Long Short-Term Memory architectures for ASR, we design a novel front-end for context-sensitive Tandem feature extraction and show how the Connectionist Temporal Classification approach can be used as a BLSTM-based back-end, alternatively to Hidden Markov Models (HMM). We combine context-sensitive BLSTM-based feature generation and speech decoding techniques with source separation by convolutive non-negative matrix factorization. Applying our speaker adapted multi-stream HMM framework that processes MFCC features from NMF-enhanced speech as well as word predictions obtained via BLSTM networks and non-negative sparse classification (NSC), we obtain an average accuracy of 91.86% on the PASCAL CHiME Challenge task at signal-to-noise ratios ranging from −6 to 9 dB. To our knowledge, this is the best result ever reported for the CHiME Challenge task.

► We present a framework for robust speech recognition in high levels of non-stationary background noise and reverberation. ► Our system applies NMF for speech enhancement as well as Long Short-Term Memory to exploit contextual information. ► We evaluate three different methods to integrate bidirectional LSTM modeling into speech decoding. ► All three system variants achieve remarkable performance on the CHiME Challenge task. ► Our system outperforms the best technique proposed in the context of the PASCAL CHiME Challenge 2011.