32 citations · 38 across the 18 of their papers we have counts for
20 papers
VoxMem: Benchmarking Multimodal Memory in Large Audio Language Models
Yang Xiao, Vidhyasaharan Sethu, Eun-Jung Holden +1
Spoken conversational systems must recover information from prior interactions (i.e., memory), yet relevant information in speech extends beyond what was said to who said it, how i…
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…
Characterization of Speech Similarity Between Australian Aboriginal and High-Resource Languages: A Case Study on Dharawal
Ting Dang, Trini Manoj Jeyaseelan, Eliathamby Ambikairajah +1
Australian Aboriginal languages are of significant cultural and linguistic value but remain severely underrepresented in modern speech AI systems. While state-of-the-art speech fou…
Should Audio Front-ends be Adaptive? Comparing Learnable and Adaptive Front-ends
Qiquan Zhang, Buddhi Wickramasinghe, Eliathamby Ambikairajah +2
Hand-crafted features, such as Mel-filterbanks, have traditionally been the choice for many audio processing applications. Recently, there has been a growing interest in learnable…
Blind Estimation of Sub-band Acoustic Parameters from Ambisonics Recordings using Spectro-Spatial Covariance Features
Hanyu Meng, Jeroen Breebaart, Jeremy Stoddard +2
Estimating frequency-varying acoustic parameters is essential for enhancing immersive perception in realistic spatial audio creation. In this paper, we propose a unified framework…
A Joint Spectro-Temporal Relational Thinking Based Acoustic Modeling Framework
Zheng Nan, Ting Dang, Vidhyasaharan Sethu +1
Relational thinking refers to the inherent ability of humans to form mental impressions about relations between sensory signals and prior knowledge, and subsequently incorporate th…
AER-LLM: Ambiguity-aware Emotion Recognition Leveraging Large Language Models
Xin Hong, Yuan Gong, Vidhyasaharan Sethu +1
Recent advancements in Large Language Models (LLMs) have demonstrated great success in many Natural Language Processing (NLP) tasks. In addition to their cognitive intelligence, ex…
Dual-Constrained Dynamical Neural ODEs for Ambiguity-aware Continuous Emotion Prediction
Jingyao Wu, Ting Dang, Vidhyasaharan Sethu +1
There has been a significant focus on modelling emotion ambiguity in recent years, with advancements made in representing emotions as distributions to capture ambiguity. However, t…
Binaural Selective Attention Model for Target Speaker Extraction
Hanyu Meng, Qiquan Zhang, Xiangyu Zhang +2
The remarkable ability of humans to selectively focus on a target speaker in cocktail party scenarios is facilitated by binaural audio processing. In this paper, we present a binau…
What is Learnt by the LEArnable Front-end (LEAF)? Adapting Per-Channel Energy Normalisation (PCEN) to Noisy Conditions
Hanyu Meng, Vidhyasaharan Sethu, Eliathamby Ambikairajah
There is increasing interest in the use of the LEArnable Front-end (LEAF) in a variety of speech processing systems. However, there is a dearth of analyses of what is actually lear…
Spatial HuBERT: Self-supervised Spatial Speech Representation Learning for a Single Talker from Multi-channel Audio
Antoni Dimitriadis, Siqi Pan, Vidhyasaharan Sethu +1
Self-supervised learning has been used to leverage unlabelled data, improving accuracy and generalisation of speech systems through the training of representation models. While man…
Variational Connectionist Temporal Classification for Order-Preserving Sequence Modeling
Zheng Nan, Ting Dang, Vidhyasaharan Sethu +1
Connectionist temporal classification (CTC) is commonly adopted for sequence modeling tasks like speech recognition, where it is necessary to preserve order between the input and t…
Joint Spatio-Temporal Discretisation of Nonlinear Active Cochlear Models
T. Dang, V. Sethu, E. Ambikairajah +2
Biologically inspired auditory models play an important role in developing effective audio representations that can be tightly integrated into speech and audio processing systems.…
A Novel Markovian Framework for Integrating Absolute and Relative Ordinal Emotion Information
Jingyao Wu, Ting Dang, Vidhyasaharan Sethu +1
There is growing interest in affective computing for the representation and prediction of emotions along ordinal scales. However, the term ordinal emotion label has been used to re…
The Ambiguous World of Emotion Representation
Vidhyasaharan Sethu, Emily Mower Provost, Julien Epps +3
Artificial intelligence and machine learning systems have demonstrated huge improvements and human-level parity in a range of activities, including speech recognition, face recogni…