8 papers
LLM can Read Spectrogram: Encoder-free Speech-Language Modeling
Ruchao Fan, Yiming Wang, Yuxuan Hu +6
Recent speech-aware large language models (Speech-LLMs) rely on pre-trained speech encoders to convert audio into semantic/acoustic rich representations consumable by LLM. In this…
Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation
Yuxuan Hu, Heng Lu, Ruchao Fan +8
Strong speech-to-text (S2T) LLMs already provide robust speech perception and text reasoning, but adding speech-to-speech (S2S) output is challenging: fine-tuning the backbone can…
FlexiCodec: A Dynamic Neural Audio Codec for Low Frame Rates
Jiaqi Li, Yao Qian, Yuxuan Hu +7
Neural audio codecs are foundational to speech language models. It is expected to have a low frame rate and decoupled semantic and acoustic information. A lower frame rate codec ca…
Towards Efficient Speech-Text Jointly Decoding within One Speech Language Model
Haibin Wu, Yuxuan Hu, Ruchao Fan +8
Speech language models (Speech LMs) enable end-to-end speech-text modeling within a single model, offering a promising direction for spoken dialogue systems. The choice of speech-t…
SLM-S2ST: A multimodal language model for direct speech-to-speech translation
Yuxuan Hu, Haibin Wu, Ruchao Fan +4
Speech-aware language models (LMs) have demonstrated capabilities in understanding spoken language while generating text-based responses. However, enabling them to produce speech o…
CoVoMix2: Advancing Zero-Shot Dialogue Generation with Fully Non-Autoregressive Flow Matching
Leying Zhang, Yao Qian, Xiaofei Wang +8
Generating natural-sounding, multi-speaker dialogue is crucial for applications such as podcast creation, virtual agents, and multimedia content generation. However, existing syste…