Speech-to-Text Translation
50 papers with code • 10 benchmarks • 3 datasets
Translate audio signals of speech in one language into text in a foreign language, either in an end-to-end or cascade manner.
Benchmarks
These leaderboards are used to track progress in Speech-to-Text Translation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Speech-to-Text Translation models and implementations
MuST-C
CoVoST
Most implemented papers
fairseq S2T: Fast Speech-to-Text Modeling with fairseq
pytorch/fairseq
•
•
Asian Chapter of the Association for Computational Linguistics 2020
We introduce fairseq S2T, a fairseq extension for speech-to-text (S2T) modeling tasks such as end-to-end speech recognition and speech-to-text translation.
CoVoST 2 and Massively Multilingual Speech-to-Text Translation
Speech translation has recently become an increasingly popular topic of research, partly due to the development of benchmark datasets.
Learning Shared Semantic Space for Speech-to-Text Translation
Glaciohound/Chimera-SLT
•
•
Findings (ACL) 2021
By projecting audio and text features to a common semantic representation, Chimera unifies MT and ST tasks and boosts the performance on ST benchmarks, MuST-C and Augmented Librispeech, to a new state-of-the-art.
Lightweight Adapter Tuning for Multilingual Speech Translation
Adapter modules were recently introduced as an efficient alternative to fine-tuning in NLP.
SHAS: Approaching optimal Segmentation for End-to-End Speech Translation
mt-upc/shas
•
•
Speech translation datasets provide manual segmentations of the audios, which are not available in real-world scenarios, and existing segmentation methods usually significantly reduce translation quality at inference time.
A$^3$T: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and Editing
Recently, speech representation learning has improved many speech-related tasks such as speech recognition, speech classification, and speech-to-text translation.
PaddleSpeech: An Easy-to-Use All-in-One Speech Toolkit
PaddlePaddle/PaddleSpeech
•
•
NAACL (ACL) 2022
PaddleSpeech is an open-source all-in-one speech toolkit.
SeamlessM4T: Massively Multilingual & Multimodal Machine Translation
facebookresearch/seamless_communication
•
•
What does it take to create the Babel Fish, a tool that can help individuals translate speech between any two languages?
Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation
eske/seq2seq
•
•
This paper proposes a first attempt to build an end-to-end speech-to-text translation system, which does not use source language transcription during learning or decoding.
Augmenting Librispeech with French Translations: A Multimodal Corpus for Direct Speech Translation Evaluation
However, while large quantities of parallel texts (such as Europarl, OpenSubtitles) are available for training machine translation systems, there are no large (100h) and open source parallel corpora that include speech in a source language aligned to text in a target language.
