Automatic speech recognition on a firefighter TETRA broadcast

For a reliable keyword extraction on firefighter radio communication, a strong automatic speech recognition system is needed. However, real-life data poses several challenges like a distorted voice signal, background noise and several different speakers. Moreover, the domain is out-of-scope for common language models, and the available data is scarce. In this paper, we introduce the PRONTO corpus, which consists of German firefighter exercise transcriptions. We show that by standard adaption techniques the recognition rate already rises from virtually zero to up to 51.7 percent and can be further improved by domain-specific rules to 47.9 percent. Extending the acoustic material by semi-automatic transcription and crawled in-domain written material, we arrive at a WER of 45.2 percent.