6 papers
Towards Fine-grained Temporal Perception: Post-Training Large Audio-Language Models with Audio-Side Time Prompt
Yanfeng Shi, Pengfei Cai, Jun Liu +5
Large Audio-Language Models (LALMs) enable general audio understanding and demonstrate remarkable performance across various audio tasks. However, these models still face challenge…
A General Model for Deepfake Speech Detection: Diverse Bonafide Resources or Diverse AI-Based Generators
Lam Pham, Khoi Vu, Dat Tran +4
In this paper, we analyze two main factors of Bonafide Resource (BR) or AI-based Generator (AG) which affect the performance and the generality of a Deepfake Speech Detection (DSD)…
Detect Any Sound: Open-Vocabulary Sound Event Detection with Multi-Modal Queries
Pengfei Cai, Yan Song, Qing Gu +3
Most existing sound event detection~(SED) algorithms operate under a closed-set assumption, restricting their detection capabilities to predefined classes. While recent efforts hav…
An Efficient Transfer Learning Method Based on Adapter with Local Attributes for Speech Emotion Recognition
Haoyu Song, Ian McLoughlin, Qing Gu +2
Existing speech emotion recognition (SER) methods commonly suffer from the lack of high-quality large-scale corpus, partly due to the complex, psychological nature of emotion which…
Prototype based Masked Audio Model for Self-Supervised Learning of Sound Event Detection
Pengfei Cai, Yan Song, Nan Jiang +2
A significant challenge in sound event detection (SED) is the effective utilization of unlabeled data, given the limited availability of labeled data due to high annotation costs.…
MAT-SED: A Masked Audio Transformer with Masked-Reconstruction Based Pre-training for Sound Event Detection
Pengfei Cai, Yan Song, Kang Li +2
Sound event detection (SED) methods that leverage a large pre-trained Transformer encoder network have shown promising performance in recent DCASE challenges. However, they still r…