5 papers
Audio Tokens as a Budgeted Resource: Marginal-Utility Allocation for Scalable Audio Representations
Mingyu Zhao, Jinchao Zhang, Zhiyong Wu
Discrete audio tokens are widely used as a representation interface, yet fixed-depth RVQ tokenizers allocate equal capacity to every frame despite varying refinement value. We intr…
UniStream: Multi-Expert Residual Vector Quantization for 48 kHz Causal Streaming Audio Coding
Mingyu Zhao, Zhiyong Wu
We present UniStream, a fully causal 48 kHz neural audio codec for streaming speech, music, and environmental sounds. At its core is Multi-Expert Residual Vector Quantization (ME-R…
BAMU: Bitstream-Aware Marginal-Utility Allocation for Frozen Pretrained Neural Speech Codecs
Mingyu Zhao, Zijian Lin, Yutang Feng +6
Pretrained neural speech codecs typically use a fixed residual vector quantization (RVQ) depth for all frames, ignoring temporal variation in quantization difficulty. We propose BA…
SPG-Codec: Exploring the Role and Boundaries of Semantic Priors in Ultra-Low-Bitrate Neural Speech Coding
Mingyu Zhao, Zijian Lin, Kun Wei +1
Conventional neural speech codecs suffer from severe intelligibility degradation at ultra-low bitrates, where the bottleneck transitions from acoustic distortion to semantic loss.…
CAPAA: Classifier-Agnostic Projector-Based Adversarial Attack
Zhan Li, Mingyu Zhao, Xin Dong +2
Projector-based adversarial attack aims to project carefully designed light patterns (i.e., adversarial projections) onto scenes to deceive deep image classifiers. It has potential…