18 papers
BiEAR: A Human Auditory-Inspired Adaptive Binaural Front-end for Multi-Speaker Localisation and Distance Estimation
Hanyu Meng, Eliathamby Ambikairajah, Vidhyasaharan Sethu +2
We present BiEAR, a human auditory-inspired adaptive binaural front-end for multi-speaker localisation and distance estimation. Inspired by medial olivocochlear (MOC) feedback in h…
The WER Trap: Shattering the Illusion of Unified Tokens in Speech Language Models
Xiangyu Zhang, Yuxin Li, Haoyang Zhang +5
The pursuit of a "unified" discrete token for both speech understanding and generation has led the Speech Language Model (SLM) community to heavily rely on Word Error Rate (WER) --…
Benchmarking Gaslighting Attacks Against Speech Large Language Models
Jinyang Wu, Bin Zhu, Xiandong Zou +3
As Speech Large Language Models (Speech LLMs) become increasingly integrated into voice-based applications, ensuring their robustness against manipulative or adversarial input beco…
Code-switching Speech Recognition Under the Lens: Model- and Data-Centric Perspectives
Hexin Liu, Haoyang Zhang, Qiquan Zhang +4
Code-switching automatic speech recognition (CS-ASR) presents unique challenges due to language confusion introduced by spontaneous intra-sentence switching and accent bias that bl…
Quantizer-Aware Hierarchical Neural Codec Modeling for Speech Deepfake Detection
Jinyang Wu, Zihan Pan, Qiquan Zhang +2
Neural audio codecs discretize speech via residual vector quantization (RVQ), forming a coarse-to-fine hierarchy across quantizers. While codec models have been explored for repres…
Adaptive Per-Channel Energy Normalization Front-end for Robust Audio Signal Processing
Hanyu Meng, Vidhyasaharan Sethu, Eliathamby Ambikairajah +2
In audio signal processing, learnable front-ends have shown strong performance across diverse tasks by optimizing task-specific representation. However, their parameters remain fix…