10 papers
Hybrid Continual Learning for Low-Resource Australian Aboriginal Language Identification
Pravina Mylvaganam, Ting Dang, Eliathamby Ambikairajah +2
Language identification is an important step toward integrating endangered Australian Aboriginal languages (AALs) into speech technologies supporting language revitalisation and di…
Which Languages Transfer Best to Warlpiri? A Similarity-Based Study for Low-Resource ASR
Pravina Mylvaganam, Eliathamby Ambikairajah, Ting Dang +2
This paper investigates how language similarity can improve cross-lingual transfer for automatic speech recognition (ASR) in extremely low-resource settings. Warlpiri, an Australia…
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…
Why Can't They Remember? Uncovering Representation and Retrieval Bottlenecks in Multi-Turn Acoustic Memory
Yang Xiao, Siyi Wang, Han Yin +4
Large audio language models (LALMs) process both speech and environmental acoustic cues, yet struggle to retain non-speech information across multi-turn interactions. The performan…
Beyond Deep Learning: Speech Segmentation and Phone Classification with Neural Assemblies
Trevor Adelson, Vidhyasaharan Sethu, Ting Dang
Deep learning dominates speech processing but relies on massive datasets, global backpropagation-guided weight updates, and produces entangled representations. Assembly Calculus (A…
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…