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

TL;DR

This paper introduces a multitask Transformer model that jointly transcribes speech and generates subtitles, leveraging subtitle data to improve automatic speech recognition, especially for spontaneous and conversational speech.

Contribution

It presents a novel dual-decoder Transformer architecture that jointly performs ASR and subtitling without needing subtitle preprocessing, enhancing recognition of spontaneous speech.

Findings

Improved ASR performance on spontaneous speech datasets

Effective use of subtitle data without preprocessing

Enhanced recognition accuracy with joint training

Abstract

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.