KY
Kai Yu
cs.CLeess.AScs.SDcs.AIcs.LGcs.CVcs.HCcs.MMquant-phBiomarkers
On Valency
published · living versionsW_725xggce·v1 · currentpublished
GigaSpeech 3: Scaling Multi-Dialect Arabic Speech Recognition with Weakly Labeled Data
with Junzhe Liu, Yujie Tu, Yifan Yang, Peng Wang +11
1 version
W_eya96vf8·v1published
W_r7f9bwa4·v1published
W_fg6qkvz8·v1published
W_pyq66456·v1published
Preprints & journals
143 papers in the corpus · 2008–2026ProductWebGen: Benchmarking Multimodal Product Webpage Generation2606.01022v1 · Zhihong Liu, Siqi Kou, Zheng Li et al.2026 · 0 citationsarXiv
Anonymization, Not Elimination: Utility-Preserved Speech Anonymization2604.17000v1 · Yunchong Xiao, Yuxiang Zhao, Ziyang Ma et al.2026 · 0 citationsarXiv
Recent Advances in Discrete Speech Tokens: A Review.41385436 · Guo, Yiwei, Li, Zhihan, Wang, Hankun et al.2026 · 16 citationsIEEE transactions on pattern analysis and machine intelligence. 2026;48(4):4184-4204
PACER: Blockwise Pre-verification for Speculative Decoding with Adaptive Length2602.01274v1 · Situo Zhang, Yifan Zhang, Zichen Zhu et al.2026 · 0 citationsarXiv
SLAM-LLM: A Modular, Open-Source Multimodal Large Language Model Framework and Best Practice for Speech, Language, Audio and Music Processing2601.09385v1 · Ziyang Ma, Guanrou Yang, Wenxi Chen et al.2026 · 4 citationsarXiv
What Does the Speaker Embedding Encode?2512.18286v1 · Shuai Wang, Yanmin Qian, Kai Yu2025 · 55 citationsarXiv
TASU: Text-Only Alignment for Speech Understanding2511.03310v2 · Jing Peng, Yi Yang, Xu Li et al.2025 · 0 citationsarXiv
ISA-Bench: Benchmarking Instruction Sensitivity for Large Audio Language Models2510.23558v1 · Bohan Li, Wenbin Huang, Yuhang Qiu et al.2025 · 0 citationsarXiv
Cross-Lingual F5-TTS: Towards Language-Agnostic Voice Cloning and Speech Synthesis2509.14579v4 · Qingyu Liu, Yushen Chen, Zhikang Niu et al.2025 · 1 citationarXiv
MOSA: Mixtures of Simple Adapters Outperform Monolithic Approaches in LLM-based Multilingual ASR2508.18998v3 · Junjie Li, Jing Peng, Yangui Fang et al.2025 · 0 citationsarXiv
Joint decoding method for controllable contextual speech recognition based on Speech LLM2508.08585v1 · Yangui Fang, Jing Peng, Yu Xi et al.2025 · 0 citationsarXiv
Text adaptation for speaker verification with speaker-text factorized embeddings2508.04425v1 · Yexin Yang, Shuai Wang, Xun Gong et al.2025 · 12 citationsarXiv
Robust and Efficient Autoregressive Speech Synthesis with Dynamic Chunk-wise Prediction Policy2506.22023v1 · Bohan Li, Zhihan Li, Haoran Wang et al.2025 · 1 citationarXiv
CodecSlime: Temporal Redundancy Compression of Neural Speech Codec via Dynamic Frame Rate2506.21074v2 · Hankun Wang, Yiwei Guo, Chongtian Shao et al.2025 · 1 citationarXiv
Low-Resource Domain Adaptation for Speech LLMs via Text-Only Fine-Tuning2506.05671v2 · Yangui Fang, Jing Peng, Xu Li et al.2025 · 3 citationsarXiv
Masked Self-distilled Transducer-based Keyword Spotting with Semi-autoregressive Decoding2505.24820v1 · Yu Xi, Xiaoyu Gu, Haoyu Li et al.2025 · 1 citationarXiv
Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency2505.22515v1 · Haoran Wang, Guanyu Chen, Bohan Li et al.2025 · 0 citationsarXiv
HiDream-I1: A High-Efficient Image Generative Foundation Model with Sparse Diffusion Transformer2505.22705v1 · Qi Cai, Jingwen Chen, Yang Chen et al.2025 · 2 citationsarXiv
MFA-KWS: Effective Keyword Spotting with Multi-head Frame-asynchronous Decoding2505.19577v3 · Yu Xi, Haoyu Li, Xiaoyu Gu et al.2025 · 3 citationsarXiv
Accelerating Flow-Matching-Based Text-to-Speech via Empirically Pruned Step Sampling2505.19931v2 · Qixi Zheng, Yushen Chen, Zhikang Niu et al.2025 · 0 citationsarXiv
VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining2505.21527v2 · Jianheng Zhuo, Yifan Yang, Yiwen Shao et al.2025 · 1 citationarXiv
Unlocking Temporal Flexibility: Neural Speech Codec with Variable Frame Rate2505.16845v1 · Hanglei Zhang, Yiwei Guo, Zhihan Li et al.2025 · 5 citationsarXiv
MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix2505.13032v1 · Ziyang Ma, Yinghao Ma, Yanqiao Zhu et al.2025 · 4 citationsarXiv
Enhancing Speech-to-Speech Dialogue Modeling with End-to-End Retrieval-Augmented Generation2505.00028v2 · Pengchao Feng, Ziyang Ma, Wenxi Chen et al.2025 · 2 citationsFindings of the Association for Computational Linguistics: EMNLP 2025, pages 4499-4507
Pseudo-Autoregressive Neural Codec Language Models for Efficient Zero-Shot Text-to-Speech Synthesis2504.10352v3 · Yifan Yang, Shujie Liu, Jinyu Li et al.2025 · 1 citationarXiv
Alignment for Efficient Tool Calling of Large Language Models2503.06708v1 · Hongshen Xu, Zihan Wang, Zichen Zhu et al.2025 · 7 citationsarXiv
Enhancing LLM Reliability via Explicit Knowledge Boundary Modeling2503.02233v4 · Hang Zheng, Hongshen Xu, Yuncong Liu et al.2025 · 0 citationsarXiv
Neural Directed Speech Enhancement with Dual Microphone Array in High Noise Scenario2412.18141v2 · Wen Wen, Qiang Zhou, Yu Xi et al.2024 · 3 citationsarXiv
Why Do Speech Language Models Fail to Generate Semantically Coherent Outputs? A Modality Evolving Perspective2412.17048v2 · Hankun Wang, Haoran Wang, Yiwei Guo et al.2024 · 0 citationsarXiv
Streaming Keyword Spotting Boosted by Cross-layer Discrimination Consistency2412.12635v2 · Yu Xi, Haoyu Li, Xiaoyu Gu et al.2024 · 7 citationsarXiv
Reducing Tool Hallucination via Reliability Alignment2412.04141v3 · Hongshen Xu, Zichen Zhu, Lei Pan et al.2024 · 2 citationsarXiv
Unified Pathological Speech Analysis with Prompt Tuning2411.04142v1 · Fei Yang, Xuenan Xu, Mengyue Wu et al.2024 · 0 citationsarXiv
A Survey on Speech Large Language Models for Understanding2410.18908v6 · Jing Peng, Yucheng Wang, Bohan Li et al.2024 · 16 citationsarXiv
MobA: Multifaceted Memory-Enhanced Adaptive Planning for Efficient Mobile Task Automation2410.13757v3 · Zichen Zhu, Hao Tang, Yansi Li et al.2024 · 3 citationsarXiv
SLAM-AAC: Enhancing Audio Captioning with Paraphrasing Augmentation and CLAP-Refine through LLMs2410.09503v1 · Wenxi Chen, Ziyang Ma, Xiquan Li et al.2024 · 8 citationsarXiv
F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching2410.06885v3 · Yushen Chen, Zhikang Niu, Ziyang Ma et al.2024 · 93 citationsarXiv
ChemDFM-X: Towards Large Multimodal Model for Chemistry2409.13194v2 · Zihan Zhao, Bo Chen, Jingpiao Li et al.2024 · 11 citationsarXiv
vec2wav 2.0: Advancing Voice Conversion via Discrete Token Vocoders2409.01995v4 · Yiwei Guo, Zhihan Li, Junjie Li et al.2024 · 0 citationsarXiv
Semi-supervised Learning for Code-Switching ASR with Large Language Model Filter2407.04219v2 · Yu Xi, Wen Ding, Kai Yu et al.2024 · 4 citationsarXiv
Text-aware Speech Separation for Multi-talker Keyword Spotting2406.12447v1 · Haoyu Li, Baochen Yang, Yu Xi et al.2024 · 9 citationsarXiv
FakeSound: Deepfake General Audio Detection2406.08052v1 · Zeyu Xie, Baihan Li, Xuenan Xu et al.2024 · 15 citationsarXiv
Evolving Subnetwork Training for Large Language Models2406.06962v1 · Hanqi Li, Lu Chen, Da Ma et al.2024 · 1 citationarXiv
Sparsity-Accelerated Training for Large Language Models2406.01392v2 · Da Ma, Lu Chen, Pengyu Wang et al.2024 · 0 citationsarXiv
AniTalker: Animate Vivid and Diverse Talking Faces through Identity-Decoupled Facial Motion Encoding2405.03121v1 · Tao Liu, Feilong Chen, Shuai Fan et al.2024 · 20 citationsarXiv
CoE-SQL: In-Context Learning for Multi-Turn Text-to-SQL with Chain-of-Editions2405.02712v1 · Hanchong Zhang, Ruisheng Cao, Hongshen Xu et al.2024 · 13 citationsarXiv
StoryTTS: A Highly Expressive Text-to-Speech Dataset with Rich Textual Expressiveness Annotations2404.14946v1 · Sen Liu, Yiwei Guo, Xie Chen et al.2024 · 3 citationsIEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024, pp. 11521-11525
The X-LANCE Technical Report for Interspeech 2024 Speech Processing Using Discrete Speech Unit Challenge2404.06079v2 · Yiwei Guo, Chenrun Wang, Yifan Yang et al.2024 · 0 citationsarXiv
TDT-KWS: Fast And Accurate Keyword Spotting Using Token-and-duration Transducer2403.13332v1 · Yu Xi, Hao Li, Baochen Yang et al.2024 · 9 citationsarXiv
A Detailed Audio-Text Data Simulation Pipeline using Single-Event Sounds2403.04594v1 · Xuenan Xu, Xiaohang Xu, Zeyu Xie et al.2024 · 5 citationsarXiv
Enhancing Audio Generation Diversity with Visual Information2403.01278v1 · Zeyu Xie, Baihan Li, Xuenan Xu et al.2024 · 2 citationsarXiv
Career total: 458 works. 143 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.