MOSS-Speech: Towards True Speech-to-Speech Models Without Text Guidance
Abstract
MOSS-Speech is a speech-to-speech large language model that directly processes and generates speech without text intermediates, achieving state-of-the-art performance in spoken question answering and competitive text performance.
Spoken dialogue systems often rely on cascaded pipelines that transcribe, process, and resynthesize speech. While effective, this design discards paralinguistic cues and limits expressivity. Recent end-to-end methods reduce latency and better preserve these cues, yet still rely on text intermediates, creating a fundamental bottleneck. We present MOSS-Speech, a true speech-to-speech large language model that directly understands and generates speech without relying on text guidance. Our approach combines a modality-based layer-splitting architecture with a frozen pre-training strategy, preserving the reasoning and knowledge of pretrained text LLMs while adding native speech capabilities. Experiments show that our model achieves state-of-the-art results in spoken question answering and delivers comparable speech-to-speech performance relative to existing text-guided systems, while still maintaining competitive text performance. By narrowing the gap between text-guided and direct speech generation, our work establishes a new paradigm for expressive and efficient end-to-end speech interaction.
Community
True Speech-to-speech Model
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- UniSS: Unified Expressive Speech-to-Speech Translation with Your Voice (2025)
- DualSpeechLM: Towards Unified Speech Understanding and Generation via Dual Speech Token Modeling with Large Language Models (2025)
- MGM-Omni: Scaling Omni LLMs to Personalized Long-Horizon Speech (2025)
- EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMs (2025)
- Comprehend and Talk: Text to Speech Synthesis via Dual Language Modeling (2025)
- Think Before You Talk: Enhancing Meaningful Dialogue Generation in Full-Duplex Speech Language Models with Planning-Inspired Text Guidance (2025)
- Cross-Modal Knowledge Distillation for Speech Large Language Models (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper