8 accepted papers
Speech Large Language Models (SLLMs) enable high-level emotion reasoning, but often produce ungrounded, text-biased judgments without verifiable acoustic evidence. In contrast, SSL encoders such as WavLM yield strong acoustic representations yet remain opaque discriminative models that offer limited…
Preference learning has gained significant attention in tasks involving subjective human judgments, such as speech emotion recognition (SER) and image aesthetic assessment. While pairwise frameworks such as RankNet offer robust modeling of relative preferences, they are inherently limited to local c
This work addresses the challenge of building speech emotion recognition models that generalize effectively across different domains, particularly when only limited target domain data is available with or without emotional label information. Traditional models often struggle with cross-domain perfor…
Human state detection and behavior prediction have seen significant advancements with the rise of machine learning and multimodal sensing technologies. However, predicting prosocial behavior intentions in mobility scenarios, such as helping others on the road, is an underexplored area. Current resea…
Self-supervised learning (SSL) from unlabelled speech data has revolutionized speech representation learning. Among them, wavLM, wav2vec2, HuBERT, and Data2vec have produced benchmark performances on automatic speech recognition. However, few studies have explored the generalization of SSL-based rep…
Retrieving speech samples that have specific expressive content has many applications. It is desirable to build a preference learning framework that ranks speech samples according to emotional attribute values that generalize well to new domains. A popular architecture for preference learning is the…
In this work, we proposed a method for recording device classification using the recorded speech signal. With the rapid increase in different mobile and professional recording devices, determining the source device has many applications in forensics and in further improving various speech-based appl…
In this work, we propose a new feature based on formants for whispered speaker verification (SV) task, where neutral data is used for enrollment and whispered recordings are used for test. Such a mismatch between enrollment and test often degrades the performance of whispered SV systems due to the d…