Consecutive Decoding for Speech-to-text Translation
This work addresses the problem of efficient speech-to-text translation for applications like real-time communication, though it is incremental as it builds on existing paradigms.
The paper tackles the challenge of speech-to-text translation by proposing COSTT, which uses a single decoder to generate both source transcript and target translation, resulting in performance that matches or exceeds previous state-of-the-art methods on three datasets.
Speech-to-text translation (ST), which directly translates the source language speech to the target language text, has attracted intensive attention recently. However, the combination of speech recognition and machine translation in a single model poses a heavy burden on the direct cross-modal cross-lingual mapping. To reduce the learning difficulty, we propose COnSecutive Transcription and Translation (COSTT), an integral approach for speech-to-text translation. The key idea is to generate source transcript and target translation text with a single decoder. It benefits the model training so that additional large parallel text corpus can be fully exploited to enhance the speech translation training. Our method is verified on three mainstream datasets, including Augmented LibriSpeech English-French dataset, IWSLT2018 English-German dataset, and TED English-Chinese dataset. Experiments show that our proposed COSTT outperforms or on par with the previous state-of-the-art methods on the three datasets. We have released our code at \url{https://github.com/dqqcasia/st}.