Yongmao Zhang

Yongmao Zhang

Auto-generated profile, based on publicly available information

Yongmao Zhang

Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 August 2023
Verified
Conference Paper
Open access
GLGuanghou Liu
Guanghou Liu
YZYongmao Zhang
Yongmao Zhang
YLYi Lei
Yi Lei
YCYunlin Chen
Yunlin Chen
RWRui Wang
Rui Wang
ZLZhifei Li
Zhifei Li

7 February 2024 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Verified
Journal Article
Closed access
XZXinfa Zhu
Xinfa Zhu
YLYi Lei
Yi Lei
TLTao Li
Tao Li
YZYongmao Zhang
Yongmao Zhang
HZHongbin Zhou
Hongbin Zhou
LXLei Xie
Lei Xie
Previous multilingual text-to-speech (TTS) approaches have considered leveraging monolingual speaker data to enable cross-lingual speech synthesis. However, such data-efficient approaches have ignored synthesizing emotional aspects of speech due to the challenges of cross-speaker cross-lingual emotion transfer – the heavy entanglement of speaker timbre , emotion and language factors in the speech signal will make a system to produce cross-lingual synthetic speech with an undesired foreign accent and weak emotion expressiveness. This paper proposes a Multilingual Emotional TTS (METTS) model to mitigate these problems, realizing both cross-speaker and cross-lingual emotion transfer. Specifically, METTS takes DelightfulTTS as the backbone model and proposes the following designs. First, to alleviate the foreign accent problem, METTS introduces multi-scale emotion modeling to disentangle speech prosody into coarse-grained and fine-grained scales, producing language-agnostic and language-specific emotion representations, respectively. Second, as a pre-processing step, formant shift based information perturbation is applied to the reference signal for better disentanglement of speaker timbre in the speech. Third, a vector quantization based emotion matcher is designed for reference selection, leading to decent naturalness and emotion diversity in cross-lingual synthetic speech. Experiments demonstrate the good design of METTS.

2 November 2022 in arXiv
Verified
Preprint
Open access
PDF file
KSKun Song
Kun Song
HXHeyang Xue
Heyang Xue
XWXinsheng Wang
Xinsheng Wang
JCJian Cong
Jian Cong
YZYongmao Zhang
Yongmao Zhang
DSDan Su
Dan Su
Speaker adaptation in text-to-speech synthesis (TTS) is to finetune a pre-trained TTS model to adapt to new target speakers with limited data. While much effort has been conducted towards this task, seldom work has been performed for low computational resource scenarios due to the challenges raised by the requirement of the lightweight model and less computational complexity. In this paper, a tiny VITS-based TTS model, named AdaVITS, for low computing resource speaker adaptation is proposed. To effectively reduce parameters and computational complexity of VITS, an iSTFT-based wave construction decoder is proposed to replace the upsampling-based decoder which is resource-consuming in the original VITS. Besides, NanoFlow is introduced to share the density estimate across flow blocks to reduce the parameters of the prior encoder. Furthermore, to reduce the computational complexity of the textual encoder, scaled-dot attention is replaced with linear attention. To deal with the instability caused by the simplified model, instead of using the original text encoder, phonetic posteriorgram (PPG) is utilized as linguistic feature via a text-to-PPG module, which is then used as input for the encoder. Experiment shows that AdaVITS can generate stable and natural speech in speaker adaptation with 8.97M model parameters and 0.72GFlops computational complexity.