Sitemap

An indoor acoustic simulation engine and WebGL workbench for room impulse response generation. Parametric rooms, floor plans, microphone arrays, and moving sources share one research workflow.
GitHub

From device meshes to multichannel acoustic transfer functions. A geometry-aware simulation workflow for microphone arrays on devices, robot heads, and smart glasses.
GitHub

Zhiqi Ai, Zhiyong Chen, Shugong Xu
Text and speech enrollment for multilingual, user-defined keyword spotting.
Paper · PDF · Code

Zhiyong Chen, Zhiqi Ai, Xinnuo Li, Shugong Xu
Rapid enrollment-time tuning for open-set speaker identification.
Paper · arXiv

Zhiyong Chen^*, Zhiqi Ai^*, Youxuan Ma, Xinnuo Li, Shugong Xu
A two-branch speaker control module for improved voice cloning and zero-shot speaker adaptation.
Paper · Demo

Zhiyong Chen, Xinnuo Li, Zhiqi Ai, Shugong Xu
Multimodal style and speaker control with enhanced feature fusion for zero-shot speech synthesis.
Paper · arXiv · Demo

Zhiyong Chen, Shuhang Wu, Xinnuo Li, Zhiqi Ai, Shugong Xu
Few-shot tuning and speech synthesis to address aging and emotional variation in speaker recognition.
Paper · PDF

Zhiqi Ai, Meixuan Bao, Zhiyong Chen, Zhi Yang, Xinnuo Li, Shugong Xu
A longitudinal dataset for studying speaker aging and its effects on speaker verification.
Paper · Code · Dataset

Zhiyong Chen, Xinnuo Li, Shuhang Wu, Zhi Yang, Zhiqi Ai, Shugong Xu
Consistency flow matching for efficient denoising acoustic decoding in text-to-speech synthesis.
Paper · Code · Demo

Zhiyong Chen, Shuhang Wu, Xinnuo Li, Zhiqi Ai, Shugong Xu
Few-shot open-set speaker identification with reciprocal points and synthesized or real unknown samples.
Paper

Bo Wu, Zhiqi Ai, Jun Jiang, Congcong Zhu, Shugong Xu
Stage-wise adaptive label distributions for modeling ambiguity in facial age estimation.
Paper · PDF

Shiyi Mu, Zichong Gu, Zhiqi Ai, Yilin Gao, Shugong Xu
Dual-decoder stereo transformers for efficient 3D object detection and out-of-distribution road anomaly detection.
Paper · arXiv · Code

Zhiqi Ai, Han Cheng, Shiyi Mu, Xinnuo Li, Yongjin Zhou, Shugong Xu
Dual-stage matching, multimodal enrollment, and lightweight adaptation for personalized keyword spotting.
Paper · arXiv · Code

Zhiqi Ai, Han Cheng, Yuxin Wang, Shiyi Mu, Yongjin Zhou, Shugong Xu
Scaling acoustic data and phoneme-matching anchors for robust user-defined wake words.
Paper · arXiv · Dataset

Zhiqi Ai, Han Cheng, Shiyi Mu, Zhiyong Chen, Yongjin Zhou, Shugong Xu
Hybrid enrollment and neural re-scoring for reliable verification from short speech segments.
Paper · PDF

Zhiqi Ai, Han Cheng, Shiyi Mu, Yongjin Zhou, Shugong Xu
Phoneme-level retrieval and selective correction for contextual biasing in speech language models.
Paper · Code

Shiyi Mu, Zichong Gu, Zhiqi Ai, Anqi Liu, Yilin Gao, Shugong Xu
Collaborative work on efficient stereo-based 3D object detection.
Paper · Code

Shugong Xu, Jun Jiang, Wenjun Yu, Yilin Gao, Guangjin Pan, Shiyi Mu, Zhiqi Ai, Yuan Gao, Peigang Jiang, Cheng-Xiang Wang
Collaborative work on deep learning for wireless fingerprint positioning under practical imperfections.
Paper

Zhiqi Ai, Han Cheng, Shiyi Mu, Yongjin Zhou, Shugong Xu
Floorplan-centric acoustic simulation for editable, connected multi-room scenes and distributed speech processing, with the FP-RIR dataset spanning 15,376 residential floorplans.

Zhiqi Ai, Xu Shen, Mou Wang, Yongjin Zhou, Shugong Xu
One-step, multi-bandwidth speech extension through a cutoff-aware flow bridge, progressive consistency distillation, and adversarial refinement.