Until very recently, the generation of punctuation marks for automatic speech recognition (ASR) output has been mostly done by looking at the syntactic structure of the recognized utterances. Prosodic cues such as breaks, speech rate, pitch intonation that influence placing of punctuation marks on speech transcripts have been seldom used. We propose a method that uses recurrent neural networks, taking prosodic and lexical information into account in order to predict punctuation marks for raw ASR output. Our experiments show that an attention mechanism over parallel sequences of prosodic cues aligned with transcribed speech improves accuracy of punctuation generation.

We would like to thank Francesco Barbieri for offering his technical insights throughout this work. This work is part of the KRISTINA project, which has received funding from the European Union’s Horizon 2020 Research and Innovation Programme under the Grant Agreement number H2020-RIA-645012. The second author is partially funded by the Spanish Ministry of Economy, Industry and Competitiveness through the Ramón y Cajal program.