SOTAVerified

Speech-to-Text

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 403 papers

TitleStatusHype
PaddleSpeech: An Easy-to-Use All-in-One Speech ToolkitCode6
High-Fidelity Simultaneous Speech-To-Speech TranslationCode5
OSUM: Advancing Open Speech Understanding Models with Limited Resources in AcademiaCode3
Whisper-Flamingo: Integrating Visual Features into Whisper for Audio-Visual Speech Recognition and TranslationCode3
A Non-autoregressive Generation Framework for End-to-End Simultaneous Speech-to-Speech TranslationCode2
LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPTCode2
SeamlessM4T: Massively Multilingual & Multimodal Machine TranslationCode2
SONAR: Sentence-Level Multimodal and Language-Agnostic RepresentationsCode2
MuAViC: A Multilingual Audio-Visual Corpus for Robust Speech Recognition and Robust Speech-to-Text TranslationCode2
CVSS Corpus and Massively Multilingual Speech-to-Speech TranslationCode2
Speech Model Pre-training for End-to-End Spoken Language UnderstandingCode2
Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box FrameworkCode1
Enhancing Speech-to-Speech Dialogue Modeling with End-to-End Retrieval-Augmented GenerationCode1
MEDIBENG WHISPER TINY: A FINE-TUNED CODE-SWITCHED BENGALI-ENGLISH TRANSLATOR FOR CLINICAL APPLICATIONSCode1
DuplexMamba: Enhancing Real-time Speech Conversations with Duplex and Streaming CapabilitiesCode1
WhiSPA: Semantically and Psychologically Aligned Whisper with Self-Supervised Contrastive and Student-Teacher LearningCode1
Fine-tuning Whisper on Low-Resource Languages for Real-World ApplicationsCode1
STTATTS: Unified Speech-To-Text And Text-To-Speech ModelCode1
Denial-of-Service Poisoning Attacks against Large Language ModelsCode1
OpenOmni: A Collaborative Open Source Tool for Building Future-Ready Multimodal Conversational AgentsCode1
LLaST: Improved End-to-end Speech Translation System Leveraged by Large Language ModelsCode1
Indoor Air Quality Dataset with Activities of Daily Living in Low to Middle-income CommunitiesCode1
ArzEn-LLM: Code-Switched Egyptian Arabic-English Translation and Speech Recognition Using LLMsCode1
Automatic speech recognition for the Nepali language using CNN, bidirectional LSTM and ResNetCode1
Revisiting Interpolation Augmentation for Speech-to-Text GenerationCode1
LeaPformer: Enabling Linear Transformers for Autoregressive and Simultaneous Tasks via Learned ProportionsCode1
Brilla AI: AI Contestant for the National Science and Maths QuizCode1
Pushing the Limits of Zero-shot End-to-End Speech TranslationCode1
Benchmarking Large Multimodal Models against Common CorruptionsCode1
End-to-End Single-Channel Speaker-Turn Aware Conversational Speech TranslationCode1
Towards an AI to Win Ghana's National Science and Maths QuizCode1
ComSL: A Composite Speech-Language Model for End-to-End Speech-to-Text TranslationCode1
DUB: Discrete Unit Back-translation for Speech TranslationCode1
A Whisper transformer for audio captioning trained with synthetic captions and transfer learningCode1
Back Translation for Speech-to-text Translation Without TranscriptsCode1
PSST! Prosodic Speech Segmentation with TransformersCode1
Pre-training for Speech Translation: CTC Meets Optimal TransportCode1
Information-Transport-based Policy for Simultaneous TranslationCode1
JoeyS2T: Minimalistic Speech-to-Text Modeling with JoeyNMTCode1
Cross-modal Contrastive Learning for Speech TranslationCode1
Wav2Seq: Pre-training Speech-to-Text Encoder-Decoder Models Using Pseudo LanguagesCode1
STEMM: Self-learning with Speech-text Manifold Mixup for Speech TranslationCode1
A^3T: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and EditingCode1
Regularizing End-to-End Speech Translation with Triangular Decomposition AgreementCode1
X-Vector based voice activity detection for multi-genre broadcast speech-to-textCode1
Cross Attention Augmented Transducer Networks for Simultaneous TranslationCode1
EdiTTS: Score-based Editing for Controllable Text-to-SpeechCode1
Late reverberation suppression using U-netsCode1
Speech Emotion Recognition with Multi-Task LearningCode1
One TTS Alignment To Rule Them AllCode1
Show:102550
← PrevPage 1 of 9Next →

No leaderboard results yet.