Yuke Si

Speech Emotion Recognition with Co-Attention based Multi-level Acoustic Information

Speech Emotion Recognition (SER) aims to help the machine to understand human's subjective emotion from only audio information. However, extracting and utilizing comprehensive in-depth audio...

CNN-BLSTM Based Question Detection from Dialogs Considering Phase and Context Information

TopicKS: Topic-driven Knowledge Selection for Knowledge-grounded Dialogue Generation

Hierarchical Tagger with Multi-task Learning for Cross-domain Slot Filling

Improving Zero-shot Cross-domain Slot Filling via Transformer-based Slot Semantics Fusion

Domain-Specific Multi-Agent Dialog Policy Learning in Multi-Domain Task-Oriented Scenarios

Exploiting Explicit and Inferred Implicit Personas for Multi-turn Dialogue Generation

Adversarial Shared-Private Attention Network for Joint Slot Filling and Intent Detection

Global Monitoring of Dynamic Functional Interactions in the Brain During Chinese Verbs Perception

A Hierarchical Model for Dialog Act Recognition Considering Acoustic and Lexical Context Information

Cache: Modeling Contribution-Aware Context Hierarchically for Long-Range Dialogue State Tracking

Speech Emotion Recognition with Co-Attention Based Multi-Level Acoustic Information

BEES: A New Acoustic Task for Blended Emotion Estimation in Speech

Local and Global Context Modeling with Relation Matching Task for Dialog Act Recognition

Dialogue Act Recognition using Branch Architecture with Attention Mechanism for Imbalanced Data

Investigation of the spatiotemporal dynamics of the brain during perceiving words

Teaching Audio Models to Reason: A Unified Framework for Source- and Layer-wise Distillation

While large audio language models excel at tasks like ASR and emotion recognition, they still struggle with complex reasoning due to the modality gap between audio and text as well as the lack of...

HarmoniFuse: A Component-Selective and Prompt-Adaptive Framework for Multi-Task Speech Language Modeling

Recent advances in large language models have facilitated the development of unified speech language models (SLMs) capable of supporting multiple speech tasks within a shared architecture....