paper-with-me

홈 › Papers

Improving End-to-end Speech Translation by Leveraging Auxiliary Speech and Text Data

2022-12-04 · Yuhao Zhang, Chen Xu, Bojie Hu, Chunliang Zhang, Tong Xiao, Jingbo Zhu

We present a method for introducing a text encoder into pre-trained end-to-end speech translation systems. It enhances the ability of adapting one modality (i.e., source-language speech) to another (i.e., source-language text). Thus, the speech translation model can learn from both unlabeled and labeled data, especially when the source-language text data is abundant. Beyond this, we present a denoising method to build a robust text encoder that can deal with both normal and noisy text data. Our system sets new state-of-the-arts on the MuST-C En-De, En-Fr, and LibriSpeech En-Fr tasks.

📄 PDF Abstract BibTeX arXiv:2212.01778

Code (0)

등록된 구현이 없습니다.

Tasks

de-enDenoisingTranslation

Similar Papers 제목 키워드 기반

Improving End-to-end Speech Translation by Leveraging Auxiliary Speech and Text Data

2021-11-16 · ACL ARR November 2021 11 · Anonymous

We present a method for introducing a text encoder into pre-training end-to-end speech translation systems. It enhances the ability of adapting one modality (i.e., source-language speech) to another (i.e., source-languag…

de-enDenoisingTranslation

Direct Speech-to-speech Translation without Textual Annotation using Bottleneck Features

2022-12-12 · Junhui Zhang, Junjie Pan, Xiang Yin, Zejun Ma

Speech-to-speech translation directly translates a speech utterance to another between different languages, and has great potential in tasks such as simultaneous interpretation. State-of-art models usually contains an au…

Speech-to-Speech TranslationTranslation

Textless Direct Speech-to-Speech Translation with Discrete Speech Representation

2022-10-31 · Xinjian Li, Ye Jia, Chung-Cheng Chiu

Research on speech-to-speech translation (S2ST) has progressed rapidly in recent years. Many end-to-end systems have been proposed and show advantages over conventional cascade systems, which are often composed of recogn…

Speech-to-Speech TranslationTranslation

Multilingual Speech-to-Speech Translation into Multiple Target Languages

2023-07-17 · Hongyu Gong, Ning Dong, Sravya Popuri, Vedanuj Goswami 외

Speech-to-speech translation (S2ST) enables spoken communication between people talking in different languages. Despite a few studies on multilingual S2ST, their focus is the multilinguality on the source side, i.e., the…

Language IdentificationSpeech-to-Speech TranslationTranslation

Unified Speech-Text Pre-training for Speech Translation and Recognition

2022-04-11 · ACL 2022 5 · Yun Tang, Hongyu Gong, Ning Dong, Changhan Wang 외

We describe a method to jointly pre-train speech and text in an encoder-decoder modeling framework for speech translation and recognition. The proposed method incorporates four self-supervised and supervised subtasks for…

Decoderspeech-recognitionSpeech RecognitionTranslation