Transcribing radio news
Francis Kubala, Tasos Anastasakos, Hang Jin, Long Nguyen, Richard M. Schwartz · 2002
We have recently extended the capabilities of BBN's large-vocabulary discrete-utterance speech recognition system (BYBLOS) to operate on raw audio recordings of radio news programming. The recordings are given to the system as large monolithic waveforms without any additional side-information. Our goal is to transcribe all speech in the input with the highest accuracy possible. The problem is very challenging because radio news programming has frequent changes in speaker, speaking style, dialect, accent, topic, channel and environmental conditions. Furthermore, the monolithic input presents new problems for recognition algorithms and language models since all useful boundaries (such as speaker turns or sentence ends) are unknown.