6 papers
DepFlow: Disentangled Speech Generation to Mitigate Semantic Bias in Depression Detection
Yuxin Li, Xiangyu Zhang, Yifei Li +4
Speech is a scalable and non-invasive biomarker for early mental health screening. However, widely used depression datasets like DAIC-WOZ exhibit strong coupling between linguistic…
Step-Audio-R1 Technical Report
Fei Tian, Xiangyu Tony Zhang, Yuxin Zhang +14
Recent advances in reasoning models have demonstrated remarkable success in text and vision domains through extended chain-of-thought deliberation. However, a perplexing phenomenon…
Impact of Frame Rates on Speech Tokenizer: A Case Study on Mandarin and English
Haoyang Zhang, Hexin Liu, Xiangyu Zhang +7
The speech tokenizer plays a crucial role in recent speech tasks, generally serving as a bridge between speech signals and language models. While low-frame-rate codecs are widely e…
CASPER: A Large Scale Spontaneous Speech Dataset
Cihan Xiao, Ruixing Liang, Xiangyu Zhang +8
The success of large language models has driven interest in developing similar speech processing capabilities. However, a key challenge is the scarcity of high-quality spontaneous…
Distinctive Feature Codec: An Adaptive Efficient Speech Representation for Depression Detection
Xiangyu Zhang, Fuming Fang, Peng Gao +3
Large Language Models (LLMs) have demonstrated remarkable success across diverse fields, establishing a powerful paradigm for complex information processing. This has inspired the…
Music Tempo Estimation on Solo Instrumental Performance
Zhanhong He, Roberto Togneri, Xiangyu Zhang
Recently, automatic music transcription has made it possible to convert musical audio into accurate MIDI. However, the resulting MIDI lacks music notations such as tempo, which hin…