paper-with-me

Papers

Diffusion Synthesizer for Efficient Multilingual Speech to Speech Translation

2024-06-14 · Nameer Hirschkind, Xiao Yu, Mahesh Kumar Nandwana, Joseph Liu, Eloi DuBois, Dao Le, Nicolas Thiebaut, Colin Sinclair, Kyle Spence, Charles Shang, Zoe Abrams, Morgan McGuire

We introduce DiffuseST, a low-latency, direct speech-to-speech translation system capable of preserving the input speaker's voice zero-shot while translating from multiple source languages into English. We experiment with the synthesizer component of the architecture, comparing a Tacotron-based synthesizer to a novel diffusion-based synthesizer. We find the diffusion-based synthesizer to improve MOS and PESQ audio quality metrics by 23\% each and speaker similarity by 5\% while maintaining comparable BLEU scores. Despite having more than double the parameter count, the diffusion synthesizer has lower latency, allowing the entire model to run more than 5$\times$ faster than real-time.

📄 PDF Abstract BibTeX arXiv:2406.10223

Code (0)

등록된 구현이 없습니다.

Tasks

Speech-to-Speech TranslationTranslation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

DiffSSD: A Diffusion-Based Dataset For Speech Forensics

2024-09-19 · Kratika Bhagtani, Amit Kumar Singh Yadav, Paolo Bestagini, Edward J. Delp

Diffusion-based speech generators are ubiquitous. These methods can generate very high quality synthetic speech and several recent incidents report their malicious use. To counter such misuse, synthetic speech detectors …

TransFace: Unit-Based Audio-Visual Speech Synthesizer for Talking Head Translation

2023-12-23 · Xize Cheng, Rongjie Huang, Linjun Li, Tao Jin 외

Direct speech-to-speech translation achieves high-quality results through the introduction of discrete units obtained from self-supervised learning. This approach circumvents delays and cascading errors associated with m…

es-enfr-enSelf-Supervised LearningSpeech-to-Speech Translation+1

SpeechMatrix: A Large-Scale Mined Corpus of Multilingual Speech-to-Speech Translations

2022-11-08 · arXiv 2022 10 · Paul-Ambroise Duquenne, Hongyu Gong, Ning Dong, Jingfei Du 외

We present SpeechMatrix, a large-scale multilingual corpus of speech-to-speech translations mined from real speech of European Parliament recordings. It contains speech alignments in 136 language pairs with a total of 41…

Mixture-of-ExpertsSpeech-to-Speech TranslationTranslation

CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens

2024-07-07 · Zhihao Du, Qian Chen, Shiliang Zhang, Kai Hu 외

Recent years have witnessed a trend that large language model (LLM) based text-to-speech (TTS) emerges into the mainstream due to their high naturalness and zero-shot capacity. In this paradigm, speech signals are discre…

Language ModellingLarge Language ModelQuantizationspeech-recognition+5

FST: the FAIR Speech Translation System for the IWSLT21 Multilingual Shared Task

2021-07-14 · ACL (IWSLT) 2021 8 · Yun Tang, Hongyu Gong, Xian Li, Changhan Wang 외

In this paper, we describe our end-to-end multilingual speech translation system submitted to the IWSLT 2021 evaluation campaign on the Multilingual Speech Translation shared task. Our system is built by leveraging trans…

Transfer LearningTranslation