Speech-to-Speech Translation

27 papers with code • 3 benchmarks • 5 datasets

Speech-to-speech translation (S2ST) consists on translating speech from one language to speech in another language. This can be done with a cascade of automatic speech recognition (ASR), text-to-text machine translation (MT), and text-to-speech (TTS) synthesis sub-systems, which is text-centric. Recently, works on S2ST without relying on intermediate text representation is emerging.


Use these libraries to find Speech-to-Speech Translation models and implementations

Most implemented papers

SeamlessM4T: Massively Multilingual & Multimodal Machine Translation

facebookresearch/seamless_communication 22 Aug 2023

What does it take to create the Babel Fish, a tool that can help individuals translate speech between any two languages?

Direct speech-to-speech translation with a sequence-to-sequence model

sam2125/translatotron 12 Apr 2019

We present an attention-based sequence-to-sequence neural network which can directly translate speech from one language into speech in another language, without relying on an intermediate text representation.

Towards Automatic Face-to-Face Translation

Rudrabha/LipGAN ACM Multimedia, 2019 2019

As today's digital communication becomes increasingly visual, we argue that there is a need for systems that can automatically translate a video of a person speaking in language A into a target language B with realistic lip synchronization.

ESPnet-ST: All-in-One Speech Translation Toolkit

espnet/espnet ACL 2020

We present ESPnet-ST, which is designed for the quick development of speech-to-speech translation systems in a single framework.

Direct speech-to-speech translation with discrete units

rongjiehuang/transpeech ACL 2022

When target text transcripts are available, we design a joint speech and text training framework that enables the model to generate dual modality output (speech and text) simultaneously in the same inference pass.

Multimodal and Multilingual Embeddings for Large-Scale Speech Mining

facebookresearch/LASER NeurIPS 2021

Using a similarity metric in that multimodal embedding space, we perform mining of audio in German, French, Spanish and English from Librivox against billions of sentences from Common Crawl.

CVSS Corpus and Massively Multilingual Speech-to-Speech Translation

google-research-datasets/cvss LREC 2022

In addition, CVSS provides normalized translation text which matches the pronunciation in the translation speech.

LibriS2S: A German-English Speech-to-Speech Translation Corpus

pedrodke/libris2s LREC 2022

In contrast, the activities in the area of speech-to-speech translation is still limited, although it is essential to overcome the language barrier.

Leveraging Pseudo-labeled Data to Improve Direct Speech-to-Speech Translation

fengpeng-yue/speech-to-speech-translation 18 May 2022

Direct Speech-to-speech translation (S2ST) has drawn more and more attention recently.

TranSpeech: Speech-to-Speech Translation With Bilateral Perturbation

rongjiehuang/transpeech 25 May 2022

Specifically, a sequence of discrete representations derived in a self-supervised manner are predicted from the model and passed to a vocoder for speech reconstruction, while still facing the following challenges: 1) Acoustic multimodality: the discrete units derived from speech with same content could be indeterministic due to the acoustic property (e. g., rhythm, pitch, and energy), which causes deterioration of translation accuracy; 2) high latency: current S2ST systems utilize autoregressive models which predict each unit conditioned on the sequence previously generated, failing to take full advantage of parallelism.