ICMC-ASR：ICASSP 2024 车载多通道自动语音识别挑战赛
ICMC-ASR: The ICASSP 2024 In-Car Multi-Channel Automatic Speech Recognition Challenge
AI总结：
本文介绍 ICASSP 2024 ICMC-ASR 挑战赛，基于新能源车多通道语音和噪声数据设立 ASR 与 ASDR 双赛道，吸引 98 支队伍参赛，冠军在 CER 和 cpCER 上较基线分别提升 13.08% 和 51.4%。
摘要：
为了推动驾驶场景下的语音处理和识别研究，我们在 ISCSLP 2022 举办的智能座舱语音识别挑战赛（ICSRC）成功基础上，发起 ICASSP 2024 车载多通道自动语音识别（ICMC-ASR）挑战赛。本次挑战赛收集了超过 100 小时在一辆新能源车内录制的多通道语音数据，以及 40 小时用于数据增强的噪声数据。比赛设置了两个赛道，包括自动语音识别（ASR）和自动语音分离与识别（ASDR），分别使用字错误率（CER）和拼接最小排列字错误率（cpCER）作为评估指标。总体而言，ICMC-ASR 挑战赛吸引了 98 支参赛队伍，并在两个赛道中收到 53 份有效结果。最终，第一名队伍 USTCiflytek 在 ASR 赛道取得 13.16% 的 CER，在 ASDR 赛道取得 21.48% 的 cpCER，与挑战赛基线相比分别实现了 13.08% 和 51.4% 的绝对提升。
英文摘要：
To promote speech processing and recognition research in driving scenarios, we build on the success of the Intelligent Cockpit Speech Recognition Challenge (ICSRC) held at ISCSLP 2022 and launch the ICASSP 2024 In-Car Multi-Channel Automatic Speech Recognition (ICMC-ASR) Challenge. This challenge collects over 100 hours of multi-channel speech data recorded inside a new energy vehicle and 40 hours of noise for data augmentation. Two tracks, including automatic speech recognition (ASR) and automatic speech diarization and recognition (ASDR) are set up, using character error rate (CER) and concatenated minimum permutation character error rate (cpCER) as evaluation metrics, respectively. Overall, the ICMC-ASR Challenge attracts 98 participating teams and receives 53 valid results in both tracks. In the end, first-place team USTCiflytek achieves a CER of 13.16% in the ASR track and a cpCER of 21.48% in the ASDR track, showing an absolute improvement of 13.08% and 51.4% compared to our challenge baseline, respectively.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
