RescueSpeech: A German Corpus for Speech Recognition in Search and Rescue Domain
This addresses the problem of deploying robust speech recognition systems for real-time decision-making in search and rescue operations, though it is incremental as it focuses on dataset creation rather than novel algorithmic improvements.
The authors tackled the problem of accurately transcribing conversational and emotional speech in noisy, reverberant search and rescue (SAR) environments by creating RescueSpeech, a publicly available German speech dataset from simulated rescue exercises, along with training recipes and pre-trained models. They found that state-of-the-art methods still perform far below acceptable levels in this challenging scenario.
Despite the recent advancements in speech recognition, there are still difficulties in accurately transcribing conversational and emotional speech in noisy and reverberant acoustic environments. This poses a particular challenge in the search and rescue (SAR) domain, where transcribing conversations among rescue team members is crucial to support real-time decision-making. The scarcity of speech data and associated background noise in SAR scenarios make it difficult to deploy robust speech recognition systems. To address this issue, we have created and made publicly available a German speech dataset called RescueSpeech. This dataset includes real speech recordings from simulated rescue exercises. Additionally, we have released competitive training recipes and pre-trained models. Our study highlights that the performance attained by state-of-the-art methods in this challenging scenario is still far from reaching an acceptable level.