Learning to Jointly Transcribe and Subtitle for End-to-End Spontaneous Speech Recognition

Autor:	Poncelet, Jakob, Van hamme, Hugo
Rok vydání:	2022
Předmět:	Electrical Engineering and Systems Science - Audio and Speech Processing Computer Science - Computation and Language Computer Science - Sound
Druh dokumentu:	Working Paper
Popis:	TV subtitles are a rich source of transcriptions of many types of speech, ranging from read speech in news reports to conversational and spontaneous speech in talk shows and soaps. However, subtitles are not verbatim (i.e. exact) transcriptions of speech, so they cannot be used directly to improve an Automatic Speech Recognition (ASR) model. We propose a multitask dual-decoder Transformer model that jointly performs ASR and automatic subtitling. The ASR decoder (possibly pre-trained) predicts the verbatim output and the subtitle decoder generates a subtitle, while sharing the encoder. The two decoders can be independent or connected. The model is trained to perform both tasks jointly, and is able to effectively use subtitle data. We show improvements on regular ASR and on spontaneous and conversational ASR by incorporating the additional subtitle decoder. The method does not require preprocessing (aligning, filtering, pseudo-labeling, ...) of the subtitles. Comment: Accepted at SLT 2022
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2210.07771 Zobrazit plný text záznamu View this record from Arxiv