activity
20202022
most citedCNN-based Discriminative Training for Domain Compensation in Acoustic Event Detection with Frame-wise Classifier

3 citations · 5 across the 4 of their papers we have counts for

collaborators

5 papers

cs.SD2022

ECAPA-TDNN for Multi-speaker Text-to-speech Synthesis

Jinlong Xue, Yayue Deng, Yichen Han +3

In recent years, neural network based methods for multi-speaker text-to-speech synthesis (TTS) have made significant progress. However, the current speaker encoder models used in t…

eess.AS2022

Selective Pseudo-labeling and Class-wise Discriminative Fusion for Sound Event Detection

Yunhao Liang, Yanhua Long, Yijie Li +1

In recent years, exploring effective sound separation (SSep) techniques to improve overlapping sound event detection (SED) attracts more and more attention. Creating accurate separ…

eess.AS20213 cited

CNN-based Discriminative Training for Domain Compensation in Acoustic Event Detection with Frame-wise Classifier

Tiantian Tang, Xinyuan Zhou, Yanhua Long +2

Domain mismatch is a noteworthy issue in acoustic event detection tasks, as the target domain data is difficult to access in most real applications. In this study, we propose a nov…

eess.AS2020

Attention-based scaling adaptation for target speech extraction

Jiangyu Han, Wei Rao, Yanhua Long +1

The target speech extraction has attracted widespread attention in recent years. In this work, we focus on investigating the dynamic interaction between different mixtures and the…

eess.AS20202 cited

Self-and-Mixed Attention Decoder with Deep Acoustic Structure for Transformer-based LVCSR

Xinyuan Zhou, Grandee Lee, Emre Yılmaz +3

The Transformer has shown impressive performance in automatic speech recognition. It uses the encoder-decoder structure with self-attention to learn the relationship between the hi…