Speech-to-Text Translation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 11
- 보존된 평가 기록
- 31
Translate audio signals of speech in one language into text in a foreign language, either in an end-to-end or cascade manner.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/Glaciohound/Chimera-SLT
공식 코드Learning Shared Semantic Space for Speech-to-Text Translation
https://github.com/Glaciohound/Chimera-ST
공식 코드Learning Shared Semantic Space for Speech-to-Text Translation
https://github.com/Magic-Ma-tech/Audio-Jailbreak-Attacks
공식 코드Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework
https://github.com/PaddlePaddle/PaddleSpeech
공식 코드https://github.com/ReneeYe/XSTNet
공식 코드End-to-end Speech Translation via Cross-modal Progressive Training
https://github.com/ahmedheakl/arazn-llm
공식 코드ArzEn-LLM: Code-Switched Egyptian Arabic-English Translation and Speech Recognition Using LLMs
https://github.com/amazon-science/stac-speech-translation
공식 코드End-to-End Single-Channel Speaker-Turn Aware Conversational Speech Translation
https://github.com/asappresearch/wav2seq
공식 코드Wav2Seq: Pre-training Speech-to-Text Encoder-Decoder Models Using Pseudo Languages
https://github.com/bytedance/neurst
공식 코드https://github.com/bzhangGo/zero
공식 코드Revisiting End-to-End Speech-to-Text Translation From Scratch
https://github.com/djanibekov/rebooting-llm
공식 코드https://github.com/dlion168/Listen-and-Speak-Fairly
공식 코드Listen and Speak Fairly: A Study on Semantic Gender Bias in Speech Integrated Large Language Models
https://github.com/dqqcasia/mosst
공식 코드https://github.com/dqqcasia/st
공식 코드https://github.com/duyichao/e2e-st-tda
공식 코드Regularizing End-to-End Speech Translation with Triangular Decomposition Agreement
https://github.com/eske/seq2seq
공식 코드Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation
https://github.com/espnet/espnet
공식 코드ESPnet-ST-v2: Multipurpose Spoken Language Translation Toolkit
https://github.com/facebookresearch/covost
공식 코드CoVoST: A Diverse Multilingual Speech-To-Text Translation Corpus
https://github.com/facebookresearch/muavic
공식 코드https://github.com/facebookresearch/seamless_communication
공식 코드SeamlessM4T: Massively Multilingual & Multimodal Machine Translation
https://github.com/facebookresearch/sonar
공식 코드SONAR: Sentence-Level Multimodal and Language-Agnostic Representations
https://github.com/fdschmidt93/fleurs-slu
공식 코드Fleurs-SLU: A Massively Multilingual Benchmark for Spoken Language Understanding
https://github.com/formiel/fairseq
공식 코드Lightweight Adapter Tuning for Multilingual Speech Translation
https://github.com/formiel/fairseq/blob/master/examples/speech_to_text/docs/adapters.md
공식 코드Lightweight Adapter Tuning for Multilingual Speech Translation
https://github.com/formiel/speech-translation
공식 코드Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation
https://github.com/google-research-datasets/cvss
공식 코드CVSS Corpus and Massively Multilingual Speech-to-Speech Translation
https://github.com/gpengzhi/simcr
공식 코드An Empirical Study of Consistency Regularization for End-to-End Speech-to-Text Translation
https://github.com/hlt-mt/fbk-fairseq
공식 코드StreamAtt: Direct Streaming Speech-to-Text Translation with Attention-based Audio History Selection
https://github.com/ictnlp/bt4st
공식 코드Back Translation for Speech-to-text Translation Without Transcripts
https://github.com/ictnlp/stemm
공식 코드STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translation
https://github.com/ictnlp/streamspeech
공식 코드StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learning
https://github.com/mgaido91/FBK-fairseq-ST
공식 코드Contextualized Translation of Automatically Segmented Speech
https://github.com/mingzi151/w2v2-st
공식 코드M-Adapter: Modality Adaptation for End-to-End Speech-to-Text Translation
https://github.com/mt-upc/iwslt-2021
공식 코드End-to-End Speech Translation with Pre-trained Models and Adapters: UPC at IWSLT 2021
https://github.com/mt-upc/s2t-perceiver
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.