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.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
S2ST-Omni: An Efficient and Scalable Multilingual Speech-to-Speech Translation Framework via Seamless Speech-Text Alignment and Streaming Speech Generation
Phi-Omni-ST: A multimodal language model for direct speech-to-speech translation
Dub-S2ST: Textless Speech-to-Speech Translation for Seamless Dubbing
Leveraging Unit Language Guidance to Advance Speech Modeling in Textless Speech-to-Speech Translation
Language translation, and change of accent for speech-to-speech task using diffusion model
SimulS2S-LLM: Unlocking Simultaneous Inference of Speech LLMs for Speech-to-Speech Translation
Using Phonemes in cascaded S2S translation pipeline
Direct Speech to Speech Translation: A Review
Connecting Voices: LoReSpeech as a Low-Resource Speech Parallel Corpus
Balancing Speech Understanding and Generation Using Continual Pre-training for Codec-based Speech LLM
Speech to Speech Translation with Translatotron: A State of the Art Review
High-Fidelity Simultaneous Speech-To-Speech Translation
A Unit-based System and Dataset for Expressive Direct Speech-to-Speech Translation
Improving Lip-synchrony in Direct Audio-Visual Speech-to-Speech Translation
Direct Speech-to-Speech Neural Machine Translation: A Survey
Findings of the IWSLT 2024 Evaluation Campaign
Phonology-Guided Speech-to-Speech Translation for African Languages
Textless Streaming Speech-to-Speech Translation using Semantic Speech Tokens
Improving Speech Emotion Recognition in Under-Resourced Languages via Speech-to-Speech Translation with Bootstrapping Data Selection
What does it take to get state of the art in simultaneous speech-to-speech translation?
PolySinger: Singing-Voice to Singing-Voice Translation from English to Japanese
Preset-Voice Matching for Privacy Regulated Speech-to-Speech Translation Systems
Laugh Now Cry Later: Controlling Time-Varying Emotional States of Flow-Matching-Based Zero-Shot Text-to-Speech
Analyzing Speech Unit Selection for Textless Speech-to-Speech Translation
FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs
NAIST Simultaneous Speech Translation System for IWSLT 2024
Diffusion Synthesizer for Efficient Multilingual Speech to Speech Translation
A Non-autoregressive Generation Framework for End-to-End Simultaneous Speech-to-Speech Translation
Can We Achieve High-quality Direct Speech-to-Speech Translation without Parallel Speech Data?
CTC-based Non-autoregressive Textless Speech-to-Speech Translation
StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learning
SimulTron: On-Device Simultaneous Speech to Speech Translation
Textless Acoustic Model with Self-Supervised Distillation for Noise-Robust Expressive Speech-to-Speech Translation
Discrete Multimodal Transformers with a Pretrained Large Language Model for Mixed-Supervision Speech Processing
SeamlessExpressiveLM: Speech Language Model for Expressive Speech-to-Speech Translation with Chain-of-Thought
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.