SOTAVerified

Speech-to-Text Translation

Translate audio signals of speech in one language into text in a foreign language, either in an end-to-end or cascade manner.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 101–146 of 146 papers

TitleStatusHype
Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentation—0
XTREME-S: Evaluating Cross-lingual Speech Representations—0
Cross-modal Contrastive Learning for Speech Translation—0
Improve Sinhala Speech Recognition Through e2e LF-MMI Model—0
An Experiment on Speech-to-Text Translation Systems for Manipuri to English on Low Resource Setting—0
Decision Attentive Regularization to Improve Simultaneous Speech Translation Systems—0
Speechformer: Reducing Information Loss in Direct Speech TranslationCode0
Infusing Future Information into Monotonic Attention Through Language ModelsCode0
Improving Speech Translation by Understanding and Learning from the Auxiliary Text Translation Task—0
Pay Better Attention to Attention: Head Selection in Multilingual and Multi-Domain Sequence Modeling—0
Direct Simultaneous Speech-to-Text Translation Assisted by Synchronized Streaming ASR—0
TASK AWARE MULTI-TASK LEARNING FOR SPEECH TO TEXT TASKS—0
Towards Measuring Fairness in AI: the Casual Conversations Dataset—0
Towards the evaluation of automatic simultaneous speech translation from a communicative perspective—0
NeurST: Neural Speech Translation ToolkitCode0
Bridging the Modality Gap for Speech-to-Text Translation—0
MAM: Masked Acoustic Modeling for End-to-End Speech-to-Text Translation—0
Subtitles to Segmentation: Improving Low-Resource Speech-to-Text Translation Pipelines—0
fairseq S2T: Fast Speech-to-Text Modeling with fairseqCode0
Contextualized Translation of Automatically Segmented SpeechCode0
End-to-End Offline Speech Translation System for IWSLT 2020 using Modality Agnostic Meta-Learning—0
SimulSpeech: End-to-End Simultaneous Speech to Text Translation—0
Self-Supervised Representations Improve End-to-End Speech Translation—0
Improving Cross-Lingual Transfer Learning for End-to-End Speech Recognition with Speech Translation—0
Subtitles to Segmentation: Improving Low-Resource Speech-to-TextTranslation Pipelines—0
Synchronous Speech Recognition and Speech-to-Text Translation with Interactive DecodingCode0
A Comparative Study on End-to-end Speech to Text Translation—0
Data Efficient Direct Speech-to-Text Translation with Modality Agnostic Meta-Learning—0
Europarl-ST: A Multilingual Corpus For Speech Translation Of Parliamentary Debates—0
Analyzing ASR pretraining for low-resource speech-to-text translation—0
Instance-Based Model Adaptation For Direct Speech Translation—0
Cross-lingual topic prediction for speech using translations—0
Enhancing Transformer for End-to-end Speech-to-Text Translation—0
Direct speech-to-speech translation with a sequence-to-sequence modelCode0
Leveraging Weakly Supervised Data to Improve End-to-End Speech-to-Text Translation—0
Towards Unsupervised Speech-to-Text Translation—0
Pre-training on high-resource speech recognition improves low-resource speech-to-text translationCode0
Unsupervised Cross-Modal Alignment of Speech and Text Embedding Spaces—0
Low-Resource Speech-to-Text Translation—0
End-to-End Automatic Speech Translation of AudiobooksCode0
Augmenting Librispeech with French Translations: A Multimodal Corpus for Direct Speech Translation EvaluationCode0
Interpreting Strategies Annotation in the WAW Corpus—0
Using of heterogeneous corpora for training of an ASR system—0
Towards speech-to-text translation without speech recognition—0
Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text TranslationCode0
The USFD Spoken Language Translation System for IWSLT 2014—0
Show:102550
← PrevPage 3 of 3Next →
All datasetsMuST-C EN->DEMuST-C EN->ESMuST-C EN->FRCoVoST 2 eng-XCoVoST 2 X-engFLEURS eng-XFLEURS X-englibri-transMediBengMuST-CMuST-C EN->NL

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Task Modulation + Multitask Learning(ASR/MT) + Data AugmentationCase-sensitive sacreBLEU28.88—Unverified
2Wav2Vec2.0+mBART+AdaptorsCase-sensitive sacreBLEU28.22—Unverified
3Transformer + Meta Learning(ASR/MT) + Data AugmentationCase-sensitive sacreBLEU27.51—Unverified
4Transformer with AdaptersCase-sensitive sacreBLEU24.63—Unverified
5Dual-decoder TransformerCase-sensitive sacreBLEU23.63—Unverified
6SpeechformerCase-sensitive sacreBLEU23.6—Unverified
7Transformer + ASR PretrainCase-sensitive sacreBLEU22.8—Unverified
8Transformer + ASR PretrainCase-sensitive sacreBLEU22.7—Unverified
#ModelMetricClaimedVerifiedStatus
1Transformer with AdaptersCase-sensitive sacreBLEU28.73—Unverified
2SpeechformerCase-sensitive sacreBLEU28.5—Unverified
3Dual-decoder TransformerCase-sensitive sacreBLEU28.12—Unverified
4Transformer + ASR Pretrain + SpecAugCase-sensitive sacreBLEU27.4—Unverified
5Transformer + ASR PretrainCase-sensitive sacreBLEU26.8—Unverified
#ModelMetricClaimedVerifiedStatus
1Dual-decoder TransformerCase-sensitive sacreBLEU33.45—Unverified
2Transformer + ASR Pretrain + SpecAugCase-sensitive sacreBLEU33.3—Unverified
3Transformer + ASR PretrainCase-sensitive sacreBLEU32.3—Unverified
#ModelMetricClaimedVerifiedStatus
1SeamlessM4T LargeBLEU30.6—Unverified
2SeamlessM4T MediumBLEU26.6—Unverified
#ModelMetricClaimedVerifiedStatus
1SeamlessM4T LargeBLEU34.1—Unverified
2SeamlessM4T MediumBLEU29.8—Unverified
#ModelMetricClaimedVerifiedStatus
1SeamlessM4T LargeBLEU21.5—Unverified
2SeamlessM4T MediumBLEU19.2—Unverified
#ModelMetricClaimedVerifiedStatus
1SeamlessM4T LargeBLEU24—Unverified
2SeamlessM4T MediumBLEU20.9—Unverified
#ModelMetricClaimedVerifiedStatus
1Transformer + ASR Pretrain + SpecAugCase-insensitive sacreBLEU17.2—Unverified
2Transformer + ASR PretrainCase-insensitive sacreBLEU16.5—Unverified
#ModelMetricClaimedVerifiedStatus
1MediBeng Whisper TinyBleu0.98—Unverified
2Whisper TinyBleu0.3—Unverified
#ModelMetricClaimedVerifiedStatus
1Transformer with AdaptersSacreBLEU26.61—Unverified
2Dual-decoder TransformerSacreBLEU25.62—Unverified
#ModelMetricClaimedVerifiedStatus
1SpeechformerCase-sensitive sacreBLEU27.7—Unverified