11 papers
AMECxSV: Adaptive Metadata-Driven Embedding-Fusion Calibration for X-Lingual Speaker Verification
Xin Wei, Shi He, Yihe Yuan +3
In X-lingual automatic speaker verification (ASV), fixed front-end scores vary in reliability with language match, duration, and score source. We propose AMECxSV, an adaptive metad…
Can Conversational Temporal Dynamics Improve Depression Detection in Dyads? A Preliminary Investigation in Multi-Modality Perspectives
Hanie Kang, Huang-Cheng Chou, Sudarsana Reddy Kadiri +1
Automatic depression detection from clinical interviews typically models the semantic content and acoustic characteristics of participant speech. However, the interactional timing…
Layer-wise Cross-Lingual Depression Detection from Speech: Analysis with Contrastive Alignment
Anisha Pattanayak, Hanie Kang, Huang-Cheng Chou +2
Significant disparities exist in the diagnosis and clinical presentation of depression across different linguistic populations. Speech-based depression detection performs well mono…
Speaker-Aware Temporal Aggregation Strategies on Segment Representations for Depression Detection in Dyadic Interaction: A Benchmark Study
Anisha Pattanayak, Huang-Cheng Chou, Shrikanth Narayanan +1
Speech-based depression detection compresses features from short audio segments into one speaker-level decision, a step called temporal aggregation rarely studied on its own. Most…
Cross-Dataset, Age, and Gender Generalization: A Comprehensive Analysis of Fine-Tuning Strategies for Low-Resource Children's ASR
Abhijit Sinha, Hemant Kumar Kathania, Sudarsana Reddy Kadiri +1
The challenge associated with recognizing dysarthric speech primarily arises from pronounced acoustic variability attributed to impaired articulatory precision. Past research has d…
DSSCNet: A Transfer Learning Framework for Cross-Corpus Dysarthric Speech Severity Classification
Arnab Kumar Roy, Hemant Kumar Kathania, Paban Sapkota +2
Dysarthric speech severity classification is challenging due to speaker variability, class imbalance, and limited datasets. This study introduces DSSCNet, a deep learning model tha…
How Well Do Self-Supervised Speech Models Encode Age and Gender in Children's Speech? A Layer-Wise Analysis Across Multiple Architectures
Abhijit Sinha, Hemant Kumar Kathania, Mohit Joshi +3
Self-supervised learning (SSL) models have become a central component of modern speech processing systems, as they enable the learning of rich acoustic representations without reli…
Speaker Identity in Non-Verbal Vocalizations: Conditional Distillation and Mixture of Experts Approach
Tzu-Chieh Wei, Yi-Cheng Lin, Huang-Cheng Chou +4
As expressive text-to-speech (TTS) and voice conversion (VC) systems increasingly generate non-verbal vocalizations (NVVs) to enhance naturalness, reliable speaker verification (SV…
The False Resonance: A Critical Examination of Emotion Embedding Similarity for Speech Generation Evaluation
Yun-Shao Tsai, Yi-Cheng Lin, Huang-Cheng Chou +5
Objective metrics for emotional expressiveness are vital for speech generation, particularly in expressive synthesis and voice conversion requiring emotional prosody transfer. To q…
Attack-Dependent Robustness of Neural Audio Codecs for Adversarial ASR
Jordan Prescott, Thanathai Lertpetchpun, Shrikanth Narayanan
Neural audio codecs impose a discrete bottleneck through residual vector quantization (RVQ), making them a useful class of inference-time transformations for reducing adversarial p…
VoxEmo: Benchmarking Speech Emotion Recognition with Speech LLMs
Hezhao Zhang, Huang-Cheng Chou, Shrikanth Narayanan +1
Speech Large Language Models (LLMs) show great promise for speech emotion recognition (SER) via generative interfaces. However, shifting from closed-set classification to open text…