Papers with Code 아카이브
Speech-to-Speech Translation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 3
- 보존된 평가 기록
- 17
Speech-to-speech translation (S2ST) consists on translating speech from one language to speech in another language. This can be done with a cascade of automatic speech recognition (ASR), text-to-text machine translation (MT), and text-to-speech (TTS) synthesis sub-systems, which is text-centric. Recently, works on S2ST without relying on intermediate text representation is emerging.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/Rudrabha/LipGAN
공식 코드https://github.com/ajd12342/textless-s2st
공식 코드Textless Speech-to-Speech Translation With Limited Parallel Data
https://github.com/ajd12342/unit-speech-translation
공식 코드Textless Speech-to-Speech Translation With Limited Parallel Data
https://github.com/besacier/textless-metric
공식 코드https://github.com/choijeongsoo/av2av
공식 코드https://github.com/choijeongsoo/utut
공식 코드Textless Unit-to-Unit training for Many-to-Many Multilingual Speech-to-Speech Translation
https://github.com/espnet/espnet
공식 코드https://github.com/facebookresearch/emphassess
공식 코드EmphAssess : a Prosodic Benchmark on Assessing Emphasis Transfer in Speech-to-Speech Models
https://github.com/facebookresearch/fairseq
공식 코드UnitY: Two-pass Direct Speech-to-speech Translation with Discrete Units
https://github.com/facebookresearch/seamless_communication
공식 코드SeamlessM4T: Massively Multilingual & Multimodal Machine Translation
https://github.com/facebookresearch/stopes
공식 코드BLASER: A Text-Free Speech-to-Speech Translation Evaluation Metric
https://github.com/fengpeng-yue/speech-to-speech-translation
공식 코드Leveraging Pseudo-labeled Data to Improve Direct Speech-to-Speech Translation
https://github.com/funaudiollm/cosyvoice
공식 코드https://github.com/fungus75/phonemes_s2s_pipeline
공식 코드https://github.com/google-research-datasets/cvss
공식 코드CVSS Corpus and Massively Multilingual Speech-to-Speech Translation
https://github.com/hbwu-ntu/emoctrltts-eval
공식 코드https://github.com/hsi-che-lin/improve-ser-via-s2st
공식 코드https://github.com/ictnlp/ctc-s2ut
공식 코드CTC-based Non-autoregressive Textless Speech-to-Speech Translation
https://github.com/ictnlp/daspeech
공식 코드DASpeech: Directed Acyclic Transformer for Fast and High-quality Speech-to-Speech Translation
https://github.com/ictnlp/nast-s2x
공식 코드A Non-autoregressive Generation Framework for End-to-End Simultaneous Speech-to-Speech Translation
https://github.com/ictnlp/streamspeech
공식 코드StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learning
https://github.com/joneavila/dral
공식 코드https://github.com/kyutai-labs/hibiki
공식 코드https://github.com/liamdugan/speech-to-speech
공식 코드https://github.com/microsoft/speecht5
공식 코드Joint Pre-Training with Speech and Bilingual Text for Direct Speech to Speech Translation
https://github.com/nethermanpro/transvip
공식 코드TransVIP: Speech to Speech Translation System with Voice and Isochrony Preservation
https://github.com/openai/whisper
공식 코드https://github.com/pedrodke/libris2s
공식 코드LibriS2S: A German-English Speech-to-Speech Translation Corpus
https://github.com/steventan0110/diffnorm
공식 코드DiffNorm: Self-Supervised Normalization for Non-autoregressive Speech-to-speech Translation
https://github.com/xiaozhang521/Unit_Language
공식 코드https://github.com/yuchen005/gentranslate
공식 코드GenTranslate: Large Language Models are Generative Multilingual Speech and Machine Translators
https://github.com/RoganInglis/AudioLM
https://github.com/audioshake/alt-eval
https://github.com/briansidp/whisperbiasing
https://github.com/collabora/whisperlive
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.