6 citations · 11 across the 13 of their papers we have counts for
13 papers
SpeakerRPL v2: Robust Open-set Speaker Identification through Enhanced Few-shot Foundation Tuning and Model Fusion
Zhiyong Chen, Shuhang Wu, Yingjie Duan +2
This paper proposes an improved approach for open-set speaker identification based on pretrained speaker foundation models. Building upon the previous Speaker Reciprocal Points Lea…
RA-CLAP: Relation-Augmented Emotional Speaking Style Contrastive Language-Audio Pretraining For Speech Retrieval
Haoqin Sun, Jingguang Tian, Jiaming Zhou +8
The Contrastive Language-Audio Pretraining (CLAP) model has demonstrated excellent performance in general audio description-related tasks, such as audio retrieval. However, in the…
Learning Emotion-Invariant Speaker Representations for Speaker Verification
Jingguang Tian, Xinhui Hu, Xinkang Xu
In recent years, the rapid progress in speaker verification (SV) technology has been driven by the extraction of speaker representations based on deep learning. However, such repre…
Discrete Audio Representations for Automated Audio Captioning
Jingguang Tian, Haoqin Sun, Xinhui Hu +1
Discrete audio representations, termed audio tokens, are broadly categorized into semantic and acoustic tokens, typically generated through unsupervised tokenization of continuous…
SC-MoE: Switch Conformer Mixture of Experts for Unified Streaming and Non-streaming Code-Switching ASR
Shuaishuai Ye, Shunfei Chen, Xinhui Hu +1
In this work, we propose a Switch-Conformer-based MoE system named SC-MoE for unified streaming and non-streaming code-switching (CS) automatic speech recognition (ASR), where we d…
The RoyalFlush Automatic Speech Diarization and Recognition System for In-Car Multi-Channel Automatic Speech Recognition Challenge
Jingguang Tian, Shuaishuai Ye, Shunfei Chen +4
This paper presents our system submission for the In-Car Multi-Channel Automatic Speech Recognition (ICMC-ASR) Challenge, which focuses on speaker diarization and speech recognitio…
A Deep Representation Learning-based Speech Enhancement Method Using Complex Convolution Recurrent Variational Autoencoder
Yang Xiang, Jingguang Tian, Xinhui Hu +2
Generally, the performance of deep neural networks (DNNs) heavily depends on the quality of data representation learning. Our preliminary work has emphasized the significance of de…
LE-SSL-MOS: Self-Supervised Learning MOS Prediction with Listener Enhancement
Zili Qi, Xinhui Hu, Wangjin Zhou +4
Recently, researchers have shown an increasing interest in automatically predicting the subjective evaluation for speech synthesis systems. This prediction is a challenging task, e…
Large-Scale Learning on Overlapped Speech Detection: New Benchmark and New General System
Zhaohui Yin, Jingguang Tian, Xinhui Hu +2
Overlapped Speech Detection (OSD) is an important part of speech applications involving analysis of multi-party conversations. However, most of existing OSD systems are trained and…
The Royalflush System for VoxCeleb Speaker Recognition Challenge 2022
Jingguang Tian, Xinhui Hu, Xinkang Xu
In this technical report, we describe the Royalflush submissions for the VoxCeleb Speaker Recognition Challenge 2022 (VoxSRC-22). Our submissions contain track 1, which is for supe…
The RoyalFlush System of Speech Recognition for M2MeT Challenge
Shuaishuai Ye, Peiyao Wang, Shunfei Chen +2
This paper describes our RoyalFlush system for the track of multi-speaker automatic speech recognition (ASR) in the M2MeT challenge. We adopted the serialized output training (SOT)…
Royalflush Speaker Diarization System for ICASSP 2022 Multi-channel Multi-party Meeting Transcription Challenge
Jingguang Tian, Xinhui Hu, Xinkang Xu
This paper describes the Royalflush speaker diarization system submitted to the Multi-channel Multi-party Meeting Transcription Challenge(M2MeT). Our system comprises speech enhanc…
Tdcgan: Temporal Dilated Convolutional Generative Adversarial Network for End-to-end Speech Enhancement
Shuaishuai Ye, Xinhui Hu, Xinkang Xu
In this paper, in order to further deal with the performance degradation caused by ignoring the phase information in conventional speech enhancement systems, we proposed a temporal…