An Mcformer encoder integrating Mamba and Cgmlp for improved acoustic feature extraction

Abstract Currently, attention models based on the Conformer architecture have become mainstream in the field of speech recognition due to their integration of self-attention mechanisms and convolutional networks. However, further research indicates that Conformers still exhibit limitations in captur...

Full description

Saved in:
Bibliographic Details
Main Authors: Nurmemet Yolwas, Yongchao Li, Lixu Sun, Jian Peng, Zhiwu Sun, Yajie Wei, Yineng Cai
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-04979-1
Tags: Add Tag
No Tags, Be the first to tag this record!