Xinkang Xu

Orcid: 0009-0003-2771-1398

According to our database1, Xinkang Xu authored at least 17 papers between 2019 and 2024.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
SC-MoE: Switch Conformer Mixture of Experts for Unified Streaming and Non-streaming Code-Switching ASR.
CoRR, 2024

A Deep Representation Learning-Based Speech Enhancement Method Using Complex Convolution Recurrent Variational Autoencoder.
Proceedings of the IEEE International Conference on Acoustics, 2024

The Royalflush Automatic Speech Diarization and Recognition System for In-Car Multi-Channel Automatic Speech Recognition Challenge.
Proceedings of the IEEE International Conference on Acoustics, 2024

Learning Emotion-Invariant Speaker Representations for Speaker Verification.
Proceedings of the IEEE International Conference on Acoustics, 2024

2023
Advancing the study of Large-Scale Learning in Overlapped Speech Detection.
CoRR, 2023

Semi-supervised Multimodal Emotion Recognition with Consensus Decision-making and Label Correction.
Proceedings of the 1st International Workshop on Multimodal and Responsible Affective Computing, 2023

LE-SSL-MOS: Self-Supervised Learning MOS Prediction with Listener Enhancement.
Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2023

2022
The Royalflush System for VoxCeleb Speaker Recognition Challenge 2022.
CoRR, 2022

Royalflush Speaker Diarization System for ICASSP 2022 Multi-channel Multi-party Meeting Transcription Challenge.
CoRR, 2022

Multiple Enhancements to LSTM for Learning Emotion-Salient Features in Speech Emotion Recognition.
Proceedings of the 23rd Annual Conference of the International Speech Communication Association, 2022

The Royalflush System of Speech Recognition for M2met Challenge.
Proceedings of the IEEE International Conference on Acoustics, 2022

2021
An End-to-End Dialect Identification System with Transfer Learning from a Multilingual Automatic Speech Recognition Model.
Proceedings of the 22nd Annual Conference of the International Speech Communication Association, Interspeech 2021, Brno, Czechia, August 30, 2021

An Investigation of Using Hybrid Modeling Units for Improving End-to-End Speech Recognition System.
Proceedings of the IEEE International Conference on Acoustics, 2021

Hierarchical Prosody Analysis Improves Categorical and Dimensional Emotion Recognition.
Proceedings of the Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, 2021

2020
Data Augmentation for Code-Switch Language Modeling by Fusing Multiple Text Generation Methods.
Proceedings of the 21st Annual Conference of the International Speech Communication Association, 2020

The RoyalFlush Synthesis System for Blizzard Challenge 2020.
Proceedings of the Joint Workshop for the Blizzard Challenge and Voice Conversion Challenge 2020, 2020

2019
The RoyalFlush Synthesis System for Blizzard Challenge 2019.
Proceedings of the Blizzard Challenge 2019, Vienna, Austria, September 23, 2019, 2019


  Loading...