Multi-Head Self-Attention-Based Deep Clustering for Single-Channel Speech Separation

Multi-Head Self-Attention-Based Deep Clustering for Single-Channel Speech Separation

Turning attention to a particular speaker when many people talk simultaneously is known as the cocktail party problem. It is still a tough task that remained to be solved especially for single-channel speech separation. Inspired by the physiological phenomenon that humans tend to distinguish some at...

Full description

Bibliographic Details
Main Authors: Yanliang Jin, Chenjun Tang, Qianhong Liu, Yan Wang
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Single-channel speech separation
deep clustering
multi-head self-attention
density-based canopy K-means
Online Access:https://ieeexplore.ieee.org/document/9099802/

Internet

https://ieeexplore.ieee.org/document/9099802/

Similar Items