publications

2025

1. arXiv 2025

   

   DiffSoundStream: Efficient Speech Tokenization via Diffusion Decoding

   Yang Yang, Yunpeng Li, George Sung, Shao-Fu Shih, Craig Dooley, Alessio Centazzo, and Ramanan Rajeswaran

   arXiv preprint arXiv:2506.22362 2025

   TLDR HTML

   DiffSoundStream halves the required token rate of a neural speech codec by conditioning acoustic tokens on semantic tokens to reduce redundancy, then using a distilled latent diffusion decoder to reconstruct high-quality waveforms from semantic and coarse acoustic tokens in as few as four steps.

2024

1. ICASSP 2024

   

   Binaural Angular Separation Network

   Yang Yang, George Sung, Shao-Fu Shih, Hakan Erdogan, Chehung Lee, and Matthias Grundmann

   In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2024

   TLDR HTML Google Research Blog

   A two-microphone speech separation model trained entirely on simulated RIRs that exploits TDOA "delay contrast" for angular source separation, generalizing across device geometries and running in real time on-device.

2. ICASSP 2024

   

   StreamVC: Real-Time Low-Latency Voice Conversion

   Yang Yang, Yury Kartynnik, Yunpeng Li, Jiuqiang Tang, Xing Li, George Sung, and Matthias Grundmann

   In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2024

   TLDR HTML Poster Samples

   StreamVC converts voice timbre in real time on mobile devices by combining causal soft speech units, whitened pitch features for speaker-agnostic prosody, and the SoundStream codec architecture for low-latency, high-quality synthesis.

2023

1. ICASSP 2023

   

   Guided Speech Enhancement Network

   Yang Yang, Shao-Fu Shih, Hakan Erdogan, Jamie Menjay Lin, Chehung Lee, Yunpeng Li, George Sung, and Matthias Grundmann

   In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2023

   TLDR HTML

   GSENet takes both raw microphone signals and beamformer output as input, using a contrastive training scheme to let the neural network learn spatial rejection cues from the beamformer while remaining a transferable standalone module across device form factors.

2022

1. NeurIPS 2022

   

   Neural Topological Ordering for Computation Graphs

   Mukul Gagrani, Corrado Rainone,  Yang Yang, Harris Teague, Wonseok Jeon, Roberto Bondesan, Herke Hoof, Christopher Lott, Weiliang Zeng, and Piero Zappi

   In Advances in Neural Information Processing Systems (NeurIPS) 2022

   TLDR HTML

   Topoformer, an attention-based GNN encoder paired with a priority-based decoder, learns to minimize memory usage during computation graph scheduling by generating near-optimal topological orderings of DAGs, outperforming heuristic baselines on both synthetic and real-world compiler graphs.

2. ICLR 2022

   

   Transformer-based Transform Coding

   Yinhao Zhu*,  Yang Yang*, and Taco Cohen

   In International Conference on Learning Representations (ICLR) 2022

   TLDR HTML

   A swin-transformer based auto-encoder structure is proposed that achieves SOTA in rate-distortion-complexity trade-off of image compression. It also outperforms SSF in video compression. AFAIK SwinT-ChARM is the first neural image codec that outperforms VTM in rate-distortion while with comparable decoding time on GPU.

2021

1. ICIP 2021

   

   Progressive Neural Image Compression With Nested Quantization And Latent Ordering

   Yadong Lu*, Yinhao Zhu*,  Yang Yang*, Amir Said, and Taco S Cohen

   In IEEE International Conference on Image Processing (ICIP) 2021

   TLDR HTML

   A prefix-decodable bitstream (lower bitrate stream is embedded as a prefix of higher bitrate stream) is obtained with nested quantization and per-element sorting by prior stddev, based on the hyperprior model.

2. JSP 2021

   

   Transform Network Architectures for Deep Learning Based End-to-End Image/Video Coding in Subsampled Color Spaces

   Hilmi Egilmez, Ankitesh Kumar Singh, Muhammed Coban, Marta Karczewicz, Yinhao Zhu,  Yang Yang, Amir Said, and Taco Cohen

   In IEEE Open Journal of Signal Processing 2021

   TLDR PDF

   PReLU can replace GDN in the hyperprior model to compress YUV (and RGB!) images without loss of coding gain.

3. CVPR-W 2021

   

   Phase Selective Convolution

   Jamie Menjay Lin, Parham Noorzad,  Yang Yang, Nojun Kwak, and Fatih Porikli

   In IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops on Embedded Vision 2021

   TLDR HTML

   A simple and effective extension of Conv+ReLU that can achieve better pareto efficiency in image classification when compared with ResNet and MobileNets

2020

1. ICASSP 2020

   

   Feedback Recurrent Autoencoder

   Yang Yang, Guillaume Sautière, J. Jon Ryu, and Taco S Cohen

   In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2020

   TLDR HTML

   Extend VAE to sequential setting for efficient representation learning of sequential data. In the application of speech compression, when paired with a neural vocoder, the proposed FRAE signifantly outperforms Opus, an open source speech codec.

2. ACCV 2020

   

   Feedback Recurrent Autoencoder for Video Compression

   Adam Golinski*, Reza Pourreza*,  Yang Yang*, Guillaume Sautière, and Taco S Cohen

   In Asian Conference on Computer Vision (ACCV) 2020

   TLDR HTML

   One of the early works that propose neural network based video codecs. A recurrent layer is introduced in the decoder to capture long-range redundancy of video content, the state of which is fed back to encoder.

3. CVPR 2020

   

   Guided Variational Autoencoder for Disentanglement Learning

   Zheng Ding*, Yifan Xu*, Weijian Xu, Gaurav Parmar,  Yang Yang, Max Welling, and Zhuowen Tu

   In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2020

   TLDR HTML

   An auxiliary decoder is used to improve the disentanglement of latent from a VAE.

4. ICML-W 2020

   Deep Generative Video Compression with Temporal Autoregressive Transforms

   Ruihan Yang, Yibo Yang, Joseph Marino,  Yang Yang, and Stephan Mandt

   In ICML 2020 Workshop on Invertible Neural Networks, Normalizing Flows, andExplicit Likelihood Models 2020

   PDF

2019

1. ICASSP 2019

   

   Automatic Grammar Augmentation for Robust Voice Command Recognition

   Yang Yang, Anusha Lalitha, Jinwon Lee, and Chris Lott

   In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2019

   TLDR HTML

   Improve voice command recognition of a light-weight acoustic model by augmenting the target command to capture variations of inputs.

2. INFOCOM 2019

   Joint Antenna Allocation and Link Scheduling in FlexRadio Networks

   Zhenzhi Qian,  Yang Yang, Kannan Srinivasan, and Ness B. Shroff

   In IEEE INFOCOM 2019

   HTML

2016

1. MobiHoc 2016

   Anonymous-Query Based Rate Control for Wireless Multicast: Approaching Optimality with Constant Feedback

   Fei Wu,  Yang Yang, Ouyang Zhang, Kannan Srinivasan, and Ness B. Shroff

   In 17th ACM International Symposium on Mobile Ad Hoc Networking and Computing (MobiHoc) 2016

   HTML

2015

1. JSAC 2015

   Constant-Delay and Constant-Feedback Moving Window Network Coding for Wireless Multicast: Design and Asymptotic Analysis

   Fei Wu, Yin Sun,  Yang Yang, Kannan Srinivasan, and Ness B. Shroff

   IEEE Journal on Selected Areas in Communications 2015

   HTML
2. INFOCOM 2015

   Scheduling in wireless networks with full-duplex cut-through transmission

   Yang Yang, and Ness B. Shroff

   In IEEE INFOCOM 2015

   HTML
3. CDC 2015

   Dynamic user association and energy control in cellular networks with renewable resources

   Yang Yang, Jiashang Liu, Prasun Sinha, and Ness B. Shroff

   In 54th IEEE Conference on Decision and Control (CDC) 2015

   HTML

2014

1. ToIT 2014

   Delay Asymptotics With Retransmissions and Incremental Redundancy Codes Over Erasure Channels

   Yang Yang, Jian Tan, Ness B. Shroff, and Hesham El Gamal

   IEEE Transactions on Information Theory 2014

   HTML
2. INFOCOM 2014

   Characterizing the achievable throughput in wireless networks with two active RF chains

   Yang Yang, Bo Chen, Kannan Srinivasan, and Ness B. Shroff

   In IEEE INFOCOM 2014

   HTML
3. WiOpt 2014

   A near-optimal randomized algorithm for uplink resource allocation in OFDMA systems

   Yang Yang, Changwon Nam, and Ness B. Shroff

   In 12th International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOpt) 2014

   HTML

2012

1. MobiHoc 2012

   Throughput of Rateless Codes over Broadcast Erasure Channels

   Yang Yang, and Ness Shroff

   In Thirteenth ACM International Symposium on Mobile Ad Hoc Networking and Computing (MobiHoc) 2012

   HTML

2011

1. INFOCOM 2011

   Delay asymptotics with retransmissions and fixed rate codes over erasure channels

   Jian Tan,  Yang Yang, Ness B. Shroff, and Hesham El Gamal

   In IEEE INFOCOM 2011

   HTML