The Fifth 'CHiME' Speech Separation and Recognition Challenge: Dataset, Task and Baselines

Abstract

The CHiME challenge series aims to advance robust automatic speech recognition (ASR) technology by promoting research at the interface of speech and language processing, signal processing, and machine learning. This paper introduces the 5th CHiME Challenge, which considers the task of distant multimicrophone conversational ASR in real home environments. Speech material was elicited using a dinner party scenario with efforts taken to capture data that is representative of natural conversational speech and recorded by 6 Kinect microphone arrays and 4 binaural microphone pairs. The challenge features a single-array track and a multiple-array track and, for each track, distinct rankings will be produced for systems focusing on robustness with respect to distant-microphone capture vs. systems attempting to address all aspects of the task including conversational language modeling. We discuss the rationale for the challenge and provide a detailed description of the data collection procedure, the task, and the baseline systems for array synchronization, speech enhancement, and conventional and end-to-end ASR.

An Investigation into the Effectiveness of Enhancement in ASR Training and Test for Chime-5 Dinner Party Transcription

“…Depending on how many arrays were available during test time, the challenge had a single (reference) array and a multiple array track. For more details about the corpus, the reader is referred to [11].…”

“…We perform experiments using data from the CHiME-5 challenge which focuses on distant multi-microphone conversational ASR in real home environments [11]. The CHiME-5 data is heavily degraded by reverberation and overlapped speech.…”

Environmental sound processing and its applications

“…The CHiME challenge was launched in 2011 to address the problem of recognizing speech recorded with multiple microphones in real, noisy environments, such as a family's living room, a cafe, a busy intersection, on public transport and in pedestrian areas . To develop noise‐robust ASR systems, various approaches based not only on speech processing but also on sound‐source separation and machine learning have been widely investigated, and ASR performance has improved significantly as a result of past challenges.…”

Advances in Online Audio-Visual Meeting Transcription

“…In addition, these methods were tested almost exclusively on small-scale segmented synthetic data and have not been applied to continuous conversational speech audio. Although the recently held CHiME-5 challenge helped the community make a step forward to a realistic setting, it still allowed the use of ground-truth speaker segments [22,23].…”