Qixin Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Qixin Wang has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Jia Jia
Department of Computer Science and Technology, BNRist, Tsinghua University, Beijing, China
4 shared publications - Zeyu Jin
Department of Computer Science and Technology, Tsinghua University, Beijing, China
4 shared publications - Songtao Zhou
Department of Computer Science and Technology, Tsinghua University, Beijing, China
2 shared publications - Xiaoyu Qin
Department of Computer Science and Technology, Tsinghua University, Beijing, China
2 shared publications - Zhiyong Wu
Tsinghua Shenzhen International Graduate School, Shenzhen, Guangdong, China
2 shared publications - Zixuan Wang
Tsinghua University, Beijing, China
2 shared publications
Latest Publications
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 6720-6729
HarmoniVox: Painting Voices to Match the Avatar's Soul
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 6720-6729
Open AccessHarmoniVox: Painting Voices to Match the Avatar's Soul
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1255-1264
SpeechCraft: A Fine-Grained Expressive Speech Dataset with Natural Language Description
Speech-language multi-modal learning presents a significant challenge due to the fine nuanced information inherent in speech styles. Therefore, a large-scale dataset providing elaborate comprehension of speech style is urgently needed to facilitate insightful interplay between speech audio and natural language. However, constructing such datasets presents a major trade-off between large-scale data collection and high-quality annotation. To tackle this challenge, we propose an automatic speech annotation system for expressiveness interpretation that annotates in-the-wild speech clips with expressive and vivid human language descriptions. Initially, speech audios are processed by a series of expert classifiers and captioning models to capture diverse speech characteristics, followed by a fine-tuned LlaMA for customized annotation generation. Unlike previous tag/templet-based annotation frameworks with limited information and diversity, our system provides in-depth understandings of speech style through tailored natural language descriptions, thereby enabling accurate and voluminous data generation for large model training. With this system, we create SpeechCraft, a fine-grained bilingual expressive speech dataset. It is distinguished by highly descriptive natural language style prompts, containing approximately 2,000 hours of audio data and encompassing over two million speech clips. Extensive experiments demonstrate that the proposed dataset significantly boosts speech-language task performance in stylist speech synthesis and speech style understanding.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1255-1264
Open AccessSpeechCraft: A Fine-Grained Expressive Speech Dataset with Natural Language Description
Speech-language multi-modal learning presents a significant challenge due to the fine nuanced information inherent in speech styles. Therefore, a large-scale dataset providing elaborate comprehension of speech style is urgently needed to facilitate insightful interplay between speech audio and natural language. However, constructing such datasets presents a major trade-off between large-scale data collection and high-quality annotation. To tackle this challenge, we propose an automatic speech annotation system for expressiveness interpretation that annotates in-the-wild speech clips with expressive and vivid human language descriptions. Initially, speech audios are processed by a series of expert classifiers and captioning models to capture diverse speech characteristics, followed by a fine-tuned LlaMA for customized annotation generation. Unlike previous tag/templet-based annotation frameworks with limited information and diversity, our system provides in-depth understandings of speech style through tailored natural language descriptions, thereby enabling accurate and voluminous data generation for large model training. With this system, we create SpeechCraft, a fine-grained bilingual expressive speech dataset. It is distinguished by highly descriptive natural language style prompts, containing approximately 2,000 hours of audio data and encompassing over two million speech clips. Extensive experiments demonstrate that the proposed dataset significantly boosts speech-language task performance in stylist speech synthesis and speech style understanding.
- Open Access
- 2 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-7
SoulSkipper: A Voice-Controlled Emotional Adaptive Game to Complement Therapy for Social Anxiety Disorder
In this paper, we introduce SoulSkipper, a voice-controlled emotional adaptive game based on the use of Cognitive Behavioral Therapy (CBT) to complement therapy for social anxiety disorder (SAD). The game allows players to interact with non-player characters (NPCs) through voice input, which helps players identify negative thoughts and practice speech performance through 1) specific social scenarios, 2) emotional adaptation, and 3) real-time voice feedback. Through our initial evaluation, we find that the combination of game elements and voice interactions helps players improve their awareness of therapeutic skills associated with SAD and face social interactions in real-life scenarios more positively.
- 2 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessSoulSkipper: A Voice-Controlled Emotional Adaptive Game to Complement Therapy for Social Anxiety Disorder
In this paper, we introduce SoulSkipper, a voice-controlled emotional adaptive game based on the use of Cognitive Behavioral Therapy (CBT) to complement therapy for social anxiety disorder (SAD). The game allows players to interact with non-player characters (NPCs) through voice input, which helps players identify negative thoughts and practice speech performance through 1) specific social scenarios, 2) emotional adaptation, and 3) real-time voice feedback. Through our initial evaluation, we find that the combination of game elements and voice interactions helps players improve their awareness of therapeutic skills associated with SAD and face social interactions in real-life scenarios more positively.
- Open Access
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 9393-9395
HoloSinger: Semantics and Music Driven Motion Generation with Octahedral Holographic Projection
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 9393-9395
Open AccessHoloSinger: Semantics and Music Driven Motion Generation with Octahedral Holographic Projection
- Open Access
Can Machine Generate Traditional Chinese Poetry? A Feigenbaum Test
Recent progress in neural learning demonstrated that machines can do well in regularized tasks, e.g., the game of Go. However, artistic activities such as poem generation are still widely regarded as human's special capability. In this paper, we demonstrate that a simple neural model can imitate human in some tasks of art generation. We particularly focus on traditional Chinese poetry, and show that machines can do as well as many contemporary poets and weakly pass the Feigenbaum Test, a variant of Turing test in professional domains. Our method is based on an attention-based recurrent neural network, which accepts a set of keywords as the theme and generates poems by looking at each keyword during the generation. A number of techniques are proposed to improve the model, including character vector initialization, attention to input and hybrid-style training. Compared to existing poetry generation methods, our model can generate much more theme-consistent and semantic-rich poems.
Open AccessCan Machine Generate Traditional Chinese Poetry? A Feigenbaum Test
Recent progress in neural learning demonstrated that machines can do well in regularized tasks, e.g., the game of Go. However, artistic activities such as poem generation are still widely regarded as human's special capability. In this paper, we demonstrate that a simple neural model can imitate human in some tasks of art generation. We particularly focus on traditional Chinese poetry, and show that machines can do as well as many contemporary poets and weakly pass the Feigenbaum Test, a variant of Turing test in professional domains. Our method is based on an attention-based recurrent neural network, which accepts a set of keywords as the theme and generates poems by looking at each keyword during the generation. A number of techniques are proposed to improve the model, including character vector initialization, attention to input and hybrid-style training. Compared to existing poetry generation methods, our model can generate much more theme-consistent and semantic-rich poems.