Learning to Jointly Transcribe and Subtitle for End-to-End Spontaneous Speech Recognition
This addresses the challenge of leveraging noisy subtitle data for ASR, particularly for spontaneous speech, though it is incremental as it builds on existing multitask and Transformer approaches.
The paper tackles the problem of using non-verbatim TV subtitles to improve automatic speech recognition (ASR) by proposing a multitask dual-decoder Transformer model that jointly performs ASR and automatic subtitling, showing improvements on regular and spontaneous ASR without requiring preprocessing of subtitles.
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.