Shaoxiang Dang

According to our database, Shaoxiang Dang authored at least 6 papers between 2021 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2025

A comprehensive study on supervised single-channel noisy speech separation with multi-task learning.

Shaoxiang Dang, Tetsuya Matsumoto, Yoshinori Takeuchi, Hiroaki Kudo

Speech Commun., 2025

2024

Developing vocal system impaired patient-aimed voice quality assessment approach using ASR representation-included multiple features.

Shaoxiang Dang, Tetsuya Matsumoto, Yoshinori Takeuchi, Takashi Tsuboi, Yasuhiro Tanaka, Daisuke Nakatsubo, Satoshi Maesawa, Ryuta Saito, Masahisa Katsuno, Hiroaki Kudo

Proceedings of the 25th Annual Conference of the International Speech Communication Association, 2024

A Separation Priority Pipeline for Single-Channel Speech Separation in Noisy Environments.

Shaoxiang Dang, Tetsuya Matsumoto, Yoshinori Takeuchi, Hiroaki Kudo

Proceedings of the IEEE International Conference on Acoustics, 2024

U-Mamba-Net: A highly efficient Mamba-based U-net style network for noisy and reverberant speech separation.

Shaoxiang Dang, Tetsuya Matsumoto, Yoshinori Takeuchi, Hiroaki Kudo

Proceedings of the Asia Pacific Signal and Information Processing Association Annual Summit and Conference, 2024

2023

Using Semi-supervised Learning for Monaural Time-domain Speech Separation with a Self-supervised Learning-based SI-SNR Estimator.

Shaoxiang Dang, Tetsuya Matsumoto, Yoshinori Takeuchi, Hiroaki Kudo

Proceedings of the 24th Annual Conference of the International Speech Communication Association, 2023

2021

A Restriction Training Recipe for Speech Separation on Sparsely Mixed Speech.

Shaoxiang Dang, Tetsuya Matsumoto, Hiroaki Kudo, Yoshinori Takeuchi

Proceedings of the Neural Information Processing - 28th International Conference, 2021