activity
20222024
most citedWenetSpeech4TTS: A 12,800-hour Mandarin TTS Corpus for Large Speech Generation Model Benchmark

1 citations · 1 across the 8 of their papers we have counts for

collaborators

8 papers

cs.SD2024

The ISCSLP 2024 Conversational Voice Clone (CoVoC) Challenge: Tasks, Results and Findings

Kangxiang Xia, Dake Guo, Jixun Yao +9

The ISCSLP 2024 Conversational Voice Clone (CoVoC) Challenge aims to benchmark and advance zero-shot spontaneous style voice cloning, particularly focusing on generating spontaneou…

eess.AS20241 cited

WenetSpeech4TTS: A 12,800-hour Mandarin TTS Corpus for Large Speech Generation Model Benchmark

Linhan Ma, Dake Guo, Kun Song +7

With the development of large text-to-speech (TTS) models and scale-up of the training data, state-of-the-art TTS systems have achieved impressive performance. In this paper, we pr…

eess.AS2024

Text-aware and Context-aware Expressive Audiobook Speech Synthesis

Dake Guo, Xinfa Zhu, Liumeng Xue +3

Recent advances in text-to-speech have significantly improved the expressiveness of synthetic speech. However, a major challenge remains in generating speech that captures the dive…

eess.AS2024

Single-Codec: Single-Codebook Speech Codec towards High-Performance Speech Generation

Hanzhao Li, Liumeng Xue, Haohan Guo +6

The multi-codebook speech codec enables the application of large language models (LLM) in TTS but bottlenecks efficiency and robustness due to multi-sequence prediction. To avoid t…

cs.SD2024

An Investigation of Time-Frequency Representation Discriminators for High-Fidelity Vocoder

Yicheng Gu, Xueyao Zhang, Liumeng Xue +2

Generative Adversarial Network (GAN) based vocoders are superior in both inference speed and synthesis quality when reconstructing an audible waveform from an acoustic representati…

cs.CL2024

Transfer the linguistic representations from TTS to accent conversion with non-parallel data

Xi Chen, Jiakun Pei, Liumeng Xue +1

Accent conversion aims to convert the accent of a source speech to a target accent, meanwhile preserving the speaker's identity. This paper introduces a novel non-autoregressive fr…