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

Showing 1120 of 146 papers

TitleStatusHype
End-to-End Single-Channel Speaker-Turn Aware Conversational Speech TranslationCode1
Investigating the Reordering Capability in CTC-based Non-Autoregressive End-to-End Speech TranslationCode1
ArzEn-LLM: Code-Switched Egyptian Arabic-English Translation and Speech Recognition Using LLMsCode1
LeaPformer: Enabling Linear Transformers for Autoregressive and Simultaneous Tasks via Learned ProportionsCode1
DUB: Discrete Unit Back-translation for Speech TranslationCode1
End-to-end Speech Translation via Cross-modal Progressive TrainingCode1
Cross-modal Contrastive Learning for Speech TranslationCode1
Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box FrameworkCode1
ComSL: A Composite Speech-Language Model for End-to-End Speech-to-Text TranslationCode1
CoVoST 2 and Massively Multilingual Speech-to-Text TranslationCode1
Show:102550
← PrevPage 2 of 15Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Task Modulation + Multitask Learning(ASR/MT) + Data AugmentationCase-sensitive sacreBLEU28.88Unverified
2Wav2Vec2.0+mBART+AdaptorsCase-sensitive sacreBLEU28.22Unverified
3Transformer + Meta Learning(ASR/MT) + Data AugmentationCase-sensitive sacreBLEU27.51Unverified
4Transformer with AdaptersCase-sensitive sacreBLEU24.63Unverified
5Dual-decoder TransformerCase-sensitive sacreBLEU23.63Unverified
6SpeechformerCase-sensitive sacreBLEU23.6Unverified
7Transformer + ASR PretrainCase-sensitive sacreBLEU22.8Unverified
8Transformer + ASR PretrainCase-sensitive sacreBLEU22.7Unverified
#ModelMetricClaimedVerifiedStatus
1Transformer with AdaptersCase-sensitive sacreBLEU28.73Unverified
2SpeechformerCase-sensitive sacreBLEU28.5Unverified
3Dual-decoder TransformerCase-sensitive sacreBLEU28.12Unverified
4Transformer + ASR Pretrain + SpecAugCase-sensitive sacreBLEU27.4Unverified
5Transformer + ASR PretrainCase-sensitive sacreBLEU26.8Unverified
#ModelMetricClaimedVerifiedStatus
1Dual-decoder TransformerCase-sensitive sacreBLEU33.45Unverified
2Transformer + ASR Pretrain + SpecAugCase-sensitive sacreBLEU33.3Unverified
3Transformer + ASR PretrainCase-sensitive sacreBLEU32.3Unverified
#ModelMetricClaimedVerifiedStatus
1SeamlessM4T LargeBLEU30.6Unverified
2SeamlessM4T MediumBLEU26.6Unverified
#ModelMetricClaimedVerifiedStatus
1SeamlessM4T LargeBLEU34.1Unverified
2SeamlessM4T MediumBLEU29.8Unverified
#ModelMetricClaimedVerifiedStatus
1SeamlessM4T LargeBLEU21.5Unverified
2SeamlessM4T MediumBLEU19.2Unverified
#ModelMetricClaimedVerifiedStatus
1SeamlessM4T LargeBLEU24Unverified
2SeamlessM4T MediumBLEU20.9Unverified
#ModelMetricClaimedVerifiedStatus
1Transformer + ASR Pretrain + SpecAugCase-insensitive sacreBLEU17.2Unverified
2Transformer + ASR PretrainCase-insensitive sacreBLEU16.5Unverified
#ModelMetricClaimedVerifiedStatus
1MediBeng Whisper TinyBleu0.98Unverified
2Whisper TinyBleu0.3Unverified
#ModelMetricClaimedVerifiedStatus
1Transformer with AdaptersSacreBLEU26.61Unverified
2Dual-decoder TransformerSacreBLEU25.62Unverified
#ModelMetricClaimedVerifiedStatus
1SpeechformerCase-sensitive sacreBLEU27.7Unverified