Class-Incremental Learning for Multi-Label Audio Classification
The article presents a new method for class-incremental learning of potentially overlapping sounds for multi-label audio classification…
Zero Shot Audio to Audio Emotion Transfer With Speaker Disentanglement
The article discusses the challenge of audio-to-audio (A2A) style transfer, especially in the context of transferring emotional…
Cross-Speaker Encoding Network for Multi-Talker Speech Recognition
The paper introduces a Cross-Speaker Encoding (CSE) network to improve multi-talker speech recognition. Current methods, single-input multiple-output…
RaD-Net: A Repairing and Denoising Network for Speech Signal Improvement
The paper discusses RaD-Net, a repairing and denoising network for speech signal improvement. The authors have improved…
HyperGANStrument: Instrument Sound Synthesis and Editing with Pitch-Invariant Hypernetworks
The paper proposes HyperGANStrument, a novel neural synthesizer that enhances the generation capability of GANStrument by introducing…
Masked Audio Generation using a Single Non-Autoregressive Transformer
The paper introduces MAGNET, a masked generative sequence modeling method that operates directly over several streams of…
Real-time and Continuous Turn-taking Prediction Using Voice Activity Projection
This article introduces a system for real-time and continuous turn-taking prediction in spoken dialogue systems (SDSs). The…
Learning Audio Concepts from Counterfactual Natural Language
The article discusses the limitations of conventional audio classification methods and introduces a novel method that incorporates…
Self-supervised speech representation and contextual text embedding for match-mismatch classification with EEG recording
The research focuses on the match-mismatch classification with EEG recording using self-supervised speech representation and contextual text…
Full-frequency dynamic convolution: a physical frequency-dependent convolution for sound event detection
The article discusses the development of a full-frequency dynamic convolution (FFDConv) for sound event detection. Traditional 2D…