11 papers
G-MaP-SE: Guided Speech Enhancement via GMM-Based Prior Matching
Yike Zhu, Ziqian Wang, Zikai Liu +5
Using speaker embeddings as conditioning can strengthen speech enhancement, but most methods either require clean enrollment audio or rely on embeddings extracted from noisy speech…
WhispSynth: Scaling Multilingual Whisper Corpus through Real Data Curation and A Novel Pitch-free Generative Framework
Tianyi Tan, Jiaxin Ye, Yuanming Zhang +4
Whisper generation is constrained by the difficulty of data collection. Because whispered speech has low acoustic amplitude, high-fidelity recording is challenging. In this paper,…
SVoice: Style-Aware Autoregressive Modeling with Enhanced Conditioning for Singing Style Conversion
Ziqian Wang, Xianjun Xia, Chuanzeng Huang +1
We present SVoice, the winning system of the Singing Voice Conversion Challenge (SVCC) 2025 for both the in-domain and zero-shot singing style conversion tracks. Built on the s…
LDCodec: A high quality neural audio codec with low-complexity decoder
Jiawei Jiang, Linping Xu, Dejun Zhang +3
Neural audio coding has been shown to outperform classical audio coding at extremely low bitrates. However, the practical application of neural audio codecs is still limited by the…
UniFlow: Unifying Speech Front-End Tasks via Continuous Generative Modeling
Ziqian Wang, Zikai Liu, Yike Zhu +6
Generative modeling has recently achieved remarkable success across image, video, and audio domains, demonstrating powerful capabilities for unified representation learning. Yet sp…
U-SAM: An audio language Model for Unified Speech, Audio, and Music Understanding
Ziqian Wang, Xianjun Xia, Xinfa Zhu +1
The text generation paradigm for audio tasks has opened new possibilities for unified audio understanding. However, existing models face significant challenges in achieving a compr…
RaD-Net 2: A causal two-stage repairing and denoising speech enhancement network with knowledge distillation and complex axial self-attention
Mingshuai Liu, Zhuangqi Chen, Xiaopeng Yan +5
In real-time speech communication systems, speech signals are often degraded by multiple distortions. Recently, a two-stage Repair-and-Denoising network (RaD-Net) was proposed with…
BS-PLCNet 2: Two-stage Band-split Packet Loss Concealment Network with Intra-model Knowledge Distillation
Zihan Zhang, Xianjun Xia, Chuanzeng Huang +2
Audio packet loss is an inevitable problem in real-time speech communication. A band-split packet loss concealment network (BS-PLCNet) targeting full-band signals was recently prop…
RaD-Net: A Repairing and Denoising Network for Speech Signal Improvement
Mingshuai Liu, Zhuangqi Chen, Xiaopeng Yan +5
This paper introduces our repairing and denoising network (RaD-Net) for the ICASSP 2024 Speech Signal Improvement (SSI) Challenge. We extend our previous framework based on a two-s…
BS-PLCNet: Band-split Packet Loss Concealment Network with Multi-task Learning Framework and Multi-discriminators
Zihan Zhang, Jiayao Sun, Xianjun Xia +3
Packet loss is a common and unavoidable problem in voice over internet phone (VoIP) systems. To deal with the problem, we propose a band-split packet loss concealment network (BS-P…
An Exploration of Task-decoupling on Two-stage Neural Post Filter for Real-time Personalized Acoustic Echo Cancellation
Zihan Zhang, Jiayao Sun, Xianjun Xia +4
Deep learning based techniques have been popularly adopted in acoustic echo cancellation (AEC). Utilization of speaker representation has extended the frontier of AEC, thus attract…