Building state-of-the-art distant speech recognition using the CHiME-4 challenge with a setup of speech enhancement baseline

TL;DR

This paper presents a state-of-the-art, reproducible speech recognition system for noisy environments, utilizing advanced beamforming, neural network acoustic models, and language modeling, achieving top challenge performance.

Contribution

The paper introduces a simplified, high-performing baseline system for the CHiME-4 challenge, combining beamforming, neural network acoustic models, and language models, with publicly available code.

Findings

Achieved 2.74% WER on real test set, second place in CHiME-4 challenge

Proposed a speech enhancement pipeline with multiple quality measures

Provided a reproducible recipe for noisy speech recognition research

Abstract

This paper describes a new baseline system for automatic speech recognition (ASR) in the CHiME-4 challenge to promote the development of noisy ASR in speech processing communities by providing 1) state-of-the-art system with a simplified single system comparable to the complicated top systems in the challenge, 2) publicly available and reproducible recipe through the main repository in the Kaldi speech recognition toolkit. The proposed system adopts generalized eigenvalue beamforming with bidirectional long short-term memory (LSTM) mask estimation. We also propose to use a time delay neural network (TDNN) based on the lattice-free version of the maximum mutual information (LF-MMI) trained with augmented all six microphones plus the enhanced data after beamforming. Finally, we use a LSTM language model for lattice and n-best re-scoring. The final system achieved 2.74\% WER for the real test set in the 6-channel track, which corresponds to the 2nd place in the challenge. In addition, the proposed baseline recipe includes four different speech enhancement measures, short-time objective intelligibility measure (STOI), extended STOI (eSTOI), perceptual evaluation of speech quality (PESQ) and speech distortion ratio (SDR) for the simulation test set. Thus, the recipe also provides an experimental platform for speech enhancement studies with these performance measures.