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.
Direct Speech-to-speech Translation without Textual Annotation using Bottleneck Features
Robust Speech Recognition via Large-Scale Weak Supervision
Dialogs Re-enacted Across Languages
Speech-to-Speech Translation For A Real-world Unwritten Language
SpeechMatrix: A Large-Scale Mined Corpus of Multilingual Speech-to-Speech Translations
Joint Pre-Training with Speech and Bilingual Text for Direct Speech to Speech Translation
Textless Direct Speech-to-Speech Translation with Discrete Speech Representation
Improving Speech-to-Speech Translation Through Unlabeled Text
A Textless Metric for Speech-to-Speech Comparison
Augmentation Invariant Discrete Representation for Generative Spoken Language Modeling
AudioLM: a Language Modeling Approach to Audio Generation
TranSpeech: Speech-to-Speech Translation With Bilateral Perturbation
Leveraging Pseudo-labeled Data to Improve Direct Speech-to-Speech Translation
SAMU-XLSR: Semantically-Aligned Multimodal Utterance-level Cross-Lingual Speech Representation
LibriS2S: A German-English Speech-to-Speech Translation Corpus
Prosodic Alignment for off-screen automatic dubbing
Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentation
Leveraging unsupervised and weakly-supervised data to improve direct speech-to-speech translation
Evaluating MT Systems: A Theoretical Framework
CVSS Corpus and Massively Multilingual Speech-to-Speech Translation
Textless Speech-to-Speech Translation on Real Data
Assessing Evaluation Metrics for Speech-to-Speech Translation
From Start to Finish: Latency Reduction Strategies for Incremental Speech Synthesis in Simultaneous Speech-to-Speech Translation
Direct Simultaneous Speech-to-Speech Translation with Variational Monotonic Multihead Attention
Translatotron 2: High-quality direct speech-to-speech translation with voice preservation
Direct speech-to-speech translation with discrete units
Simultaneous Speech-to-Speech Translation System with Neural Incremental ASR, MT, and TTS
Cross-Lingual Machine Speech Chain for Javanese, Sundanese, Balinese, and Bataks Speech Recognition and Synthesis
Fluent and Low-latency Simultaneous Speech-to-Speech Translation with Self-adaptive Training
UWSpeech: Speech to Speech Translation for Unwritten Languages
ESPnet-ST: All-in-One Speech Translation Toolkit
Towards Automatic Face-to-Face Translation
From Speech-to-Speech Translation to Automatic Dubbing
Speech-to-speech Translation between Untranscribed Unknown Languages
Direct speech-to-speech translation with a sequence-to-sequence model
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.