11 papers
Luna-TTS Family Technical Report
Feng Yin, Shuai Shi, Junjie Zheng +19
Modern text-to-speech (TTS) is dominated by autoregressive (AR) codec language models, whose left-to-right decoding brings latency that grows with utterance length, error accumulat…
JASTIN: Aligning LLMs for Zero-Shot Audio and Speech Evaluation via Natural Language Instructions
Leying Zhang, Bowen Shi, Haibin Wu +2
The rapid advancement of generative audio models has outpaced the development of robust evaluation methodologies. Existing objective metrics and general multimodal large language m…
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…
DeepASMR: LLM-Based Zero-Shot ASMR Speech Generation for Anyone of Any Voice
Leying Zhang, Tingxiao Zhou, Haiyang Sun +2
While modern Text-to-Speech (TTS) systems achieve high fidelity for read-style speech, they struggle to generate Autonomous Sensory Meridian Response (ASMR), a specialized, low-int…
Training Text-to-Speech Model with Purely Synthetic Data: Feasibility, Sensitivity, and Generalization Capability
Tingxiao Zhou, Leying Zhang, Zhengyang Chen +1
The potential of synthetic data in text-to-speech (TTS) model training has gained increasing attention, yet its rationality and effectiveness require systematic validation. In this…
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…