The study presents the ICASSP 2024 In-Car Multi-Channel Automatic Speech Recognition (ICMC-ASR) Challenge. This competition, which follows the success of the Intelligent Cockpit Speech Recognition Challenge, collects over 100 hours of multi-channel speech data recorded inside a new energy vehicle and 40 hours of noise for data augmentation. The challenge includes two tracks: automatic speech recognition (ASR) and automatic speech diarization and recognition (ASDR). It attracted 98 participating teams, and the first-place team achieved a CER of 13.16% in the ASR track and a cpCER of 21.48% in the ASDR track, showing significant improvements over the challenge baseline.
Publication date: 7 Jan 2024
Project Page: https://arxiv.org/abs/2401.03473v1
Paper: https://arxiv.org/pdf/2401.03473
