Anqi Xu

Anqi Xu

Auto-generated profile, based on publicly available information

Anqi Xu

Harbin Inst Technol, Sch Humanities & Social Sci, Shenzhen 518055, Peoples R China

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
1 January 2019 in Speech Communication
Verified
Journal Article
Closed access
MAMuhammad Swaileh Alzaidi
Muhammad Swaileh Alzaidi
YXYi Xu
Yi Xu
AXAnqi Xu
Anqi Xu

1 August 2021 in The Journal of the Acoustical Society of America
Verified
Journal Article
Open access
PDF file
PKPaul Konstantin Krug
Paul Konstantin Krug
BGBranislav Gerazov
Branislav Gerazov
DNDaniel R. van Niekerk
Daniel R. van Niekerk
AXAnqi Xu
Anqi Xu
YXYi Xu
Yi Xu
PBPeter Birkholz
Peter Birkholz
When pitch is explicitly modelled for parametric speech synthesis, microprosodic variations of the fundamental frequency f0 are usually disregarded by current intonation models. While there are numerous studies dealing with the nature and the origin of microprosody, little research has been done on its audibility and its effect on the naturalness of synthetic speech. In this work, the influence of obstruent-related microprosodic variations on the perceived naturalness of articulatory speech synthesis was studied. A small corpus of 20 German words and sentences was re-synthesized using the state-of-the-art articulatory synthesizer VocalTractLab. The pitch contours of the real utterances were extracted and fitted with the Target-Approximation-Model. After the real microprosodic variations were removed from the obtained pitch contours, synthetic variations were applied based on a microprosody model. Subsequently, multiple stimuli with different microprosody amplitudes were synthesized and evaluated in a listening experiment. The results indicate that microprosodic variations are barely audible, but can lead to a greater perceived naturalness of the synthesized speech in certain cases.


20 June 2024 in Journal of Phonetics
Verified
Journal Article
Open access
AXAnqi Xu
Anqi Xu
DNDaniel R. van Niekerk
Daniel R. van Niekerk
BGBranislav Gerazov
Branislav Gerazov
PKPaul Konstantin Krug
Paul Konstantin Krug
PBPeter Birkholz
Peter Birkholz
YXYi Xu
Yi Xu

5 April 2023 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Verified
Journal Article
Closed access
PKPaul Konstantin Krug
Paul Konstantin Krug
PBPeter Birkholz
Peter Birkholz
BGBranislav Gerazov
Branislav Gerazov
DNDaniel Rudolph van Niekerk
Daniel Rudolph van Niekerk
AXAnqi Xu
Anqi Xu
YXYi Xu
Yi Xu
This paper introduces a paradigm shift regarding vocal learning simulations, in which the communicative function of speech acquisition determines the learning process and intelligibility is considered the primary measure of learning success. Thereby, a novel approach for artificial vocal learning is presented that utilizes deep neural network-based phoneme recognition in order to calculate the speech acquisition objective function. This function guides a learning framework that involves the state-of-the-art articulatory speech synthesizer VocalTractLab as the motor-to-acoustic forward model. In this way, an extensive set of German phonemes, including most of the consonants and all stressed vowels, was produced successfully. The synthetic phonemes were rated as highly intelligible by human listeners. Furthermore, it is shown that visual speech information, such as lip and jaw movements, can be extracted from video recordings and be incorporated into the learning framework as an additional loss component during the optimization process. It was observed that this visual loss did not increase the overall intelligibility of phonemes. Instead, the visual loss acted as a regularization mechanism that facilitated the finding of more biologically plausible solutions in the articulatory domain.

1 January 2016 in Proceedings of Meetings on Acoustics
Verified
Conference Paper
Closed access
AXAnqi Xu
Anqi Xu
SLShue-Sum Leung
Shue-Sum Leung
ALAlbert Lee
Albert Lee
Studies on Western societies show that male voices with acoustic parameters encoding a large body size (low F0, narrow formant dispersion and F0 range) were considered to be attractive, while the opposite was true for female voices (e.g. [Xu et al., 2013, PLoS ONE, 8(4), e62397]). The present work investigates whether Japanese native listeners are guided by the same principles in assessing the voices of the opposite sex. We replicated the design in Xu et al. (2013) with the added parameter of creaky voice, which is prevalent in North America nowadays and hotly debated in terms of attractiveness. Thirty-four heterosexual participants (16 female) rated the attractiveness of synthetic stimuli controlling for F0 height, formant distribution, F0 range and voice quality. Results indicate that their preferences for voice quality are similar with studies on Western societies (breathy, modal >creaky, pressed/tensed). Additionally, low-pitched male voice with narrow formant dispersion and high-pitched female voices were also favorable. Interestingly, a narrow F0 range significantly lowered the attractiveness ratings, regardless of the gender of the voice, which contradicts Xu et al. (2013). These various results are discussed in light of the cross-linguistic/ cross-ethnic divergences in vocal attractiveness.