PACT: A Pragmatic Prompting Framework for Expressive and Voice-Preserving Speech-to-Speech Translation
cs.CL
Submitted: 2026-10-13
Updated: 2026-10-13
Comments: 7 pages, 2 figures, 3 tables
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Seamless: Multilingual Expressive and Streaming Speech Translation
- UniSS: Unified Expressive Speech-to-Speech Translation with Your Voice
- A Unit-based System and Dataset for Expressive Direct Speech-to-Speech Translation
- Dialogs Re-enacted Across Languages
- Representing 'how you say' with 'what you say': English corpus of focused speech and text reflecting corresponding implications
- CrossVoice: Crosslingual Prosody Preserving Cascade-S2ST using Transfer Learning
- Dub-S2ST: Textless Speech-to-Speech Translation for Seamless Dubbing
- Expressive Machine Dubbing Through Phrase-level Cross-lingual Prosody Transfer
- Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentation
- Fish-Speech: Leveraging Large Language Models for Advanced Multilingual Text-to-Speech Synthesis
- OpenVoice: Versatile Instant Voice Cloning
- XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model
- CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens
- Qwen3.5-Omni Technical Report
- SUPERB: Speech processing Universal PERformance Benchmark
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering