Textless Direct Speech-to-Speech Translation with Discrete Speech Representation
원문 초록
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 recognition, translation and synthesis sub-systems. However, most of the end-to-end systems still rely on intermediate textual supervision during training, which makes it infeasible to work for languages without written forms. In this work, we propose a novel model, Textless Translatotron, which is based on Translatotron 2, for training an end-to-end direct S2ST model without any textual supervision. Instead of jointly training with an auxiliary task predicting target phonemes as in Translatotron 2, the proposed model uses an auxiliary task predicting discrete speech representations which are obtained from learned or random speech quantizers. When a speech encoder pre-trained with unsupervised speech data is used for both models, the proposed model obtains translation quality nearly on-par with Translatotron 2 on the multilingual CVSS-C corpus as well as the bilingual Fisher Spanish-English corpus. On the latter, it outperforms the prior state-of-the-art textless model by +18.5 BLEU.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Using Phonemes in cascaded S2S translation pipeline
STEB: A Speech-to-Speech Translation Expressiveness Benchmark for Evaluating Beyond Translation Fidelity
Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs
S2ST-Omni: An Efficient and Scalable Multilingual Speech-to-Speech Translation Framework via Seamless Speech-Text Alignment and Streaming Speech Generation
Dub-S2ST: Textless Speech-to-Speech Translation for Seamless Dubbing
Language translation, and change of accent for speech-to-speech task using diffusion model
토론
이 논문과 연결된 포럼 글이 아직 없습니다.