8 papers
DiTReducio: A Training-Free Acceleration for DiT-Based TTS via Progressive Calibration
Yanru Huo, Ziyue Jiang, Zuoli Tang +2
While Diffusion Transformers (DiT) have advanced non-autoregressive (NAR) speech synthesis, their high computational demands remain an limitation. Existing DiT-based text-to-speech…
Entropy-based Coarse and Compressed Semantic Speech Representation Learning
Jialong Zuo, Guangyan Zhang, Minghui Fang +5
Discrete speech representation learning has recently attracted increasing interest in both acoustic and semantic modeling. Existing approaches typically encode 16 kHz waveforms int…
ControlSpeech: Towards Simultaneous and Independent Zero-shot Speaker Cloning and Zero-shot Language Style Control
Shengpeng Ji, Qian Chen, Wen Wang +8
In this paper, we present ControlSpeech, a text-to-speech (TTS) system capable of fully cloning the speaker's voice and enabling arbitrary control and adjustment of speaking style.…
Language-Codec: Bridging Discrete Codec Representations and Speech Language Models
Shengpeng Ji, Minghui Fang, Jialong Zuo +5
In recent years, large language models have achieved significant success in generative tasks related to speech, audio, music, and other signal domains. A crucial element of these m…
Rhythm Controllable and Efficient Zero-Shot Voice Conversion via Shortcut Flow Matching
Jialong Zuo, Shengpeng Ji, Minghui Fang +7
Zero-Shot Voice Conversion (VC) aims to transform the source speaker's timbre into an arbitrary unseen one while retaining speech content. Most prior work focuses on preserving the…
Enhancing Expressive Voice Conversion with Discrete Pitch-Conditioned Flow Matching Model
Jialong Zuo, Shengpeng Ji, Minghui Fang +8
This paper introduces PFlow-VC, a conditional flow matching voice conversion model that leverages fine-grained discrete pitch tokens and target speaker prompt information for expre…