9 citations · 24 across the 23 of their papers we have counts for
15 papers · 1 filter
SemBridge: Semantic Token Anchoring for Continuous-Latent Autoregressive Speech Generation
Hanke Xie, Haopeng Lin, Jiale Qian +13
Continuous-latent autoregressive speech generation has emerged as a promising alternative to discrete-token modeling by avoiding quantization loss and preserving richer acoustic in…
StreamVoice+: Evolving into End-to-end Streaming Zero-shot Voice Conversion
Zhichao Wang, Yuanzhe Chen, Xinsheng Wang +2
StreamVoice has recently pushed the boundaries of zero-shot voice conversion (VC) in the streaming domain. It uses a streamable language model (LM) with a context-aware approach to…
DualVC 3: Leveraging Language Model Generated Pseudo Context for End-to-end Low Latency Streaming Voice Conversion
Ziqian Ning, Shuai Wang, Pengcheng Zhu +4
Streaming voice conversion has become increasingly popular for its potential in real-time applications. The recently proposed DualVC 2 has achieved robust and high-quality streamin…
StreamVoice: Streamable Context-Aware Language Modeling for Real-time Zero-Shot Voice Conversion
Zhichao Wang, Yuanzhe Chen, Xinsheng Wang +2
Recent language model (LM) advancements have showcased impressive zero-shot voice conversion (VC) performance. However, existing LM-based VC models usually apply offline conversion…
VITS-Based Singing Voice Conversion Leveraging Whisper and multi-scale F0 Modeling
Ziqian Ning, Yuepeng Jiang, Zhichao Wang +2
This paper introduces the T23 team's system submitted to the Singing Voice Conversion Challenge 2023. Following the recognition-synthesis framework, our singing conversion model is…
MSM-VC: High-fidelity Source Style Transfer for Non-Parallel Voice Conversion by Multi-scale Style Modeling
Zhichao Wang, Xinsheng Wang, Qicong Xie +4
In addition to conveying the linguistic content from source speech to converted speech, maintaining the speaking style of source speech also plays an important role in the voice co…
LM-VC: Zero-shot Voice Conversion via Speech Generation based on Language Models
Zhichao Wang, Yuanzhe Chen, Lei Xie +2
Language model (LM) based audio generation frameworks, e.g., AudioLM, have recently achieved new state-of-the-art performance in zero-shot audio generation. In this paper, we explo…
Multi-level Temporal-channel Speaker Retrieval for Zero-shot Voice Conversion
Zhichao Wang, Liumeng Xue, Qiuqiang Kong +4
Zero-shot voice conversion (VC) converts source speech into the voice of any desired speaker using only one utterance of the speaker without requiring additional model updates. Typ…
Expressive-VC: Highly Expressive Voice Conversion with Attention Fusion of Bottleneck and Perturbation Features
Ziqian Ning, Qicong Xie, Pengcheng Zhu +5
Voice conversion for highly expressive speech is challenging. Current approaches struggle with the balancing between speaker similarity, intelligibility and expressiveness. To addr…
Delivering Speaking Style in Low-resource Voice Conversion with Multi-factor Constraints
Zhichao Wang, Xinsheng Wang, Lei Xie +3
Conveying the linguistic content and maintaining the source speech's speaking style, such as intonation and emotion, is essential in voice conversion (VC). However, in a low-resour…
Streaming Voice Conversion Via Intermediate Bottleneck Features And Non-streaming Teacher Guidance
Yuanzhe Chen, Ming Tu, Tang Li +7
Streaming voice conversion (VC) is the task of converting the voice of one person to another in real-time. Previous streaming VC methods use phonetic posteriorgrams (PPGs) extracte…
IQDUBBING: Prosody modeling based on discrete self-supervised speech representation for expressive voice conversion
Wendong Gan, Bolong Wen, Ying Yan +6
Prosody modeling is important, but still challenging in expressive voice conversion. As prosody is difficult to model, and other factors, e.g., speaker, environment and content, wh…
Multi-speaker Multi-style Text-to-speech Synthesis With Single-speaker Single-style Training Data Scenarios
Qicong Xie, Tao Li, Xinsheng Wang +4
In the existing cross-speaker style transfer task, a source speaker with multi-style recordings is necessary to provide the style for a target speaker. However, it is hard for one…
One-shot Voice Conversion For Style Transfer Based On Speaker Adaptation
Zhichao Wang, Qicong Xie, Tao Li +4
One-shot style transfer is a challenging task, since training on one utterance makes model extremely easy to over-fit to training data and causes low speaker similarity and lack of…
Enriching Source Style Transfer in Recognition-Synthesis based Non-Parallel Voice Conversion
Zhichao Wang, Xinyong Zhou, Fengyu Yang +6
Current voice conversion (VC) methods can successfully convert timbre of the audio. As modeling source audio's prosody effectively is a challenging task, there are still limitation…