YA
Yang Ai
eess.AScs.SDcs.AIcs.MMeess.SPcs.LGcs.CLcs.CVEncoder–decoderExplicit estimation
On Valency
published · living versionsW_38qap77e·v1 · currentpublished
AKDQ: Adaptive Key-Delta Quantization for Low-Bitrate RVQ-based Neural Speech Codecs
with Xiao-Hang Jiang, Zhen-Hua Ling, Ji Wu
1 version
Preprints & journals
54 papers in the corpus · 2018–2026Enhancing Neural Speech Coding with Semantic and Visual Cues2609.05076v1 · Yao Guo, Yang Ai, Hui-Peng Du et al.2026 · 0 citationsarXiv
Is Semantics Enough for Speech Mean Opinion Score Prediction?2609.03283v1 · Tianyu Lan, Yufei Shi, Yang Ai et al.2026 · 0 citationsarXiv
Neural Music Enhancement with Dual Time-Frequency Spectral Representations for Prediction and Discrimination2609.03357v1 · Fei Liu, Yang Ai, Zhen-Hua Ling2026 · 0 citationsarXiv
PACodec: A Low-bitrate Neural Speech Codec with Parallel Additive Vector Quantization2609.03363v1 · Fei Liu, Yang Ai, Xiao-Hang Jiang et al.2026 · 0 citationsarXiv
StreamWSR: Streamable and Lightweight Waveform-Domain Neural Speech Super-Resolution2609.03381v1 · Yuan Tian, Yang Ai, Hui-Peng Du et al.2026 · 0 citationsarXiv
Deep Neural Compression for RIR-Characterized Acoustic Environments with Structure-Aware Constraints2609.04085v1 · Chen-Yuan Ning, Yang Ai, Hui-Peng Du et al.2026 · 0 citationsarXiv
Soft Posterior Speaker Injection for Multi-Talker Speech Recognition2609.01287v4 · Jian Zhu, Jun Sun, Jiang Yang et al.2026 · 0 citationsarXiv
Towards Real-world Environment-aware Zero-shot Text-to-speech Synthesis via Disentangled Audio Infilling2608.03011v1 · Ye-Xin Lu, Xin Wang, Yang Ai et al.2026 · 0 citationsarXiv
UniVocal: Unified Speech-Singing Code-Switching Synthesis2606.01677v1 · Yufei Shi, Qian Chen, Wen Wang et al.2026 · 0 citationsarXiv
CFMDCTCodec: A Low-Bitrate Neural Speech Codec with Noise-Prior-aware Conditional Flow Matching for MDCT-Spectral Enhancement2605.26812v1 · Xiao-Hang Jiang, Yang Ai, Hui-Peng Du et al.2026 · 0 citationsarXiv
Ultra-Low-Bitrate Mel-Spectrogram-based Neural Speech Coding with Flow-Matching-based Refinement and Vocoding-driven Reconstruction2605.25669v1 · Hui-Peng Du, Yang Ai, Xiao-Hang Jiang et al.2026 · 0 citationsarXiv
LatentFlowSR: High-Fidelity Audio Super-Resolution via Noise-Robust Latent Flow Matching2604.09188v2 · Fei Liu, Yang Ai, Hui-Peng Du et al.2026 · 0 citationsarXiv
ParaGSE: Parallel Generative Speech Enhancement with Group-Vector-Quantization-based Neural Speech Codec2602.01793v1 · Fei Liu, Yang Ai2026 · 0 citationsarXiv
CodeSep: Low-Bitrate Codec-Driven Speech Separation with Base-Token Disentanglement and Auxiliary-Token Serial Prediction2601.12757v1 · Hui-Peng Du, Yang Ai, Xiao-Hang Jiang et al.2026 · 0 citationsarXiv
Universal Discrete-Domain Speech Enhancement2510.09974v2 · Fei Liu, Yang Ai, Ye-Xin Lu et al.2025 · 1 citationarXiv
Understanding Textual Capability Degradation in Speech LLMs via Parameter Importance Analysis2509.23755v1 · Chao Wang, Rui-Chen Zheng, Yang Ai et al.2025 · 0 citationsarXiv
A Distilled Low-Latency Neural Vocoder with Explicit Amplitude and Phase Prediction2509.13667v1 · Hui-Peng Du, Yang Ai, Zhen-Hua Ling2025 · 0 citationsarXiv
A High-Quality and Low-Complexity Streamable Neural Speech Codec with Knowledge Distillation2509.13670v1 · En-Wei Zhang, Hui-Peng Du, Xiao-Hang Jiang et al.2025 · 0 citationsarXiv
Neural Speech Separation with Parallel Amplitude and Phase Spectrum Estimation2509.13825v1 · Fei Liu, Yang Ai, Zhen-Hua Ling2025 · 0 citationsarXiv
Say More with Less: Variable-Frame-Rate Speech Tokenization via Adaptive Clustering and Implicit Duration Coding2509.04685v3 · Rui-Chen Zheng, Wenrui Liu, Hui-Peng Du et al.2025 · 1 citationarXiv
Is GAN Necessary for Mel-Spectrogram-based Neural Vocoder?2508.07711v1 · Hui-Peng Du, Yang Ai, Rui-Chen Zheng et al.2025 · 1 citationarXiv
Universal Preference-Score-based Pairwise Speech Quality Assessment2506.01455v1 · Yu-Fei Shi, Yang Ai, Zhen-Hua Ling2025 · 3 citationsarXiv
Vision-Integrated High-Quality Neural Speech Coding2505.23379v1 · Yao Guo, Yang Ai, Rui-Chen Zheng et al.2025 · 0 citationsarXiv
Explicit estimation of magnitude and phase spectra in parallel for high-quality speech enhancement.40367721 · Lu, Ye-Xin, Ai, Yang, Ling, Zhen-Hua2025 · 44 citationsNeural networks : the official journal of the International Neural Network Society. 2025;189:107562
A Streamable Neural Audio Codec with Residual Scalar-Vector Quantization for Real-Time Communication2504.06561v1 · Xiao-Hang Jiang, Yang Ai, Rui-Chen Zheng et al.2025 · 6 citationsarXiv
Incremental Disentanglement for Environment-Aware Zero-Shot Text-to-Speech Synthesis2412.16977v1 · Ye-Xin Lu, Hui-Peng Du, Zheng-Yan Sheng et al.2024 · 0 citationsarXiv
A Neural Denoising Vocoder for Clean Waveform Generation from Noisy Mel-Spectrogram based on Amplitude and Phase Predictions2411.12268v1 · Hui-Peng Du, Ye-Xin Lu, Yang Ai et al.2024 · 0 citationsarXiv
SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features2411.11232v1 · Yu-Fei Shi, Yang Ai, Ye-Xin Lu et al.2024 · 3 citationsarXiv
Pitch-and-Spectrum-Aware Singing Quality Assessment with Bias Correction and Model Fusion2411.11123v3 · Yu-Fei Shi, Yang Ai, Ye-Xin Lu et al.2024 · 1 citationarXiv
MDCTCodec: A Lightweight MDCT-based Neural Audio Codec towards High Sampling Rate and Low Bitrate Scenarios2411.00464v1 · Xiao-Hang Jiang, Yang Ai, Rui-Chen Zheng et al.2024 · 15 citationsarXiv
APCodec+: A Spectrum-Coding-Based High-Fidelity and High-Compression-Rate Neural Audio Codec with Staged Training Paradigm2410.22807v1 · Hui-Peng Du, Yang Ai, Rui-Chen Zheng et al.2024 · 4 citationsarXiv
ERVQ: Enhanced Residual Vector Quantization with Intra-and-Inter-Codebook Optimization for Neural Audio Codecs2410.12359v2 · Rui-Chen Zheng, Hui-Peng Du, Xiao-Hang Jiang et al.2024 · 12 citationsarXiv
Stage-Wise and Prior-Aware Neural Speech Phase Prediction2410.04990v1 · Fei Liu, Yang Ai, Hui-Peng Du et al.2024 · 0 citationsarXiv
Multi-Stage Speech Bandwidth Extension with Flexible Sampling Rate Control2406.02250v1 · Ye-Xin Lu, Yang Ai, Zheng-Yan Sheng et al.2024 · 4 citationsarXiv
Voice Attribute Editing with Text Prompt2404.08857v2 · Zhengyan Sheng, Yang Ai, Li-Juan Liu et al.2024 · 5 citationsarXiv
Low-Latency Neural Speech Phase Prediction based on Parallel Estimation Architecture and Anti-Wrapping Losses for Speech Generation Tasks2403.17378v1 · Yang Ai, Zhen-Hua Ling2024 · 5 citationsarXiv
APCodec: A Neural Audio Codec with Parallel Amplitude and Phase Spectrum Encoding and Decoding2402.10533v2 · Yang Ai, Xiao-Hang Jiang, Ye-Xin Lu et al.2024 · 41 citationsarXiv
Towards High-Quality and Efficient Speech Bandwidth Extension with Parallel Amplitude and Phase Prediction2401.06387v2 · Ye-Xin Lu, Yang Ai, Hui-Peng Du et al.2024 · 21 citationsarXiv
APNet2: High-quality and High-efficiency Neural Vocoder with Direct Prediction of Amplitude and Phase Spectra2311.11545v1 · Hui-Peng Du, Ye-Xin Lu, Yang Ai et al.2023 · 7 citationsarXiv
Incorporating Ultrasound Tongue Images for Audio-Visual Speech Enhancement2309.10455v2 · Rui-Chen Zheng, Yang Ai, Zhen-Hua Ling2023 · 14 citationsarXiv
Face-Driven Zero-Shot Voice Conversion with Memory-based Face-Voice Alignment2309.09470v1 · Zheng-Yan Sheng, Yang Ai, Yan-Nian Chen et al.2023 · 6 citationsarXiv
Long-frame-shift Neural Speech Phase Prediction with Spectral Continuity Enhancement and Interpolation Error Compensation2308.08850v1 · Yang Ai, Ye-Xin Lu, Zhen-Hua Ling2023 · 3 citationsarXiv
APNet: An All-Frame-Level Neural Vocoder Incorporating Direct Prediction of Amplitude and Phase Spectra2305.07952v1 · Yang Ai, Zhen-Hua Ling2023 · 19 citationsarXiv
Zero-shot personalized lip-to-speech synthesis with face image based voice control2305.14359v1 · Zheng-Yan Sheng, Yang Ai, Zhen-Hua Ling2023 · 6 citationsarXiv
Source-Filter-Based Generative Adversarial Neural Vocoder for High Fidelity Speech Synthesis2304.13270v1 · Ye-Xin Lu, Yang Ai, Zhen-Hua Ling2023 · 3 citationsMan-Machine Speech Communication, 2022, pp.68-80
Speech Reconstruction from Silent Tongue and Lip Articulation By Pseudo Target Generation and Domain Adversarial Training2304.05574v1 · Rui-Chen Zheng, Yang Ai, Zhen-Hua Ling2023 · 5 citationsarXiv
Neural Speech Phase Prediction based on Parallel Estimation Architecture and Anti-Wrapping Losses2211.15974v2 · Yang Ai, Zhen-Hua Ling2022 · 35 citationsarXiv
Enhancing Low-Quality Voice Recordings Using Disentangled Channel Factor and Neural Waveform Model2011.05038v1 · Haoyu Li, Yang Ai, Junichi Yamagishi2020 · 2 citationsarXiv
Denoising-and-Dereverberation Hierarchical Neural Vocoder for Robust Waveform Generation2011.03955v1 · Yang Ai, Haoyu Li, Xin Wang et al.2020 · 4 citationsarXiv
Online Speaker Adaptation for WaveNet-based Neural Vocoders2008.06182v1 · Qiuchen Huang, Yang Ai, Zhenhua Ling2020 · 0 citationsarXiv
Career total: 72 works. 54 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.