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

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 a...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2022-10
Main Authors: Poncelet, Jakob, Hugo Van hamme
Format: Article
Language:English
Subjects:
Automatic speech recognition
Coders
Decoders
Subtitles & subtitling
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2331-8422