A study on a feature enhancement algorithm based on Transformer model and its application
LI Junhua
DUAN Zhikui
YU Xinmei
Abstract：The Transformer model demonstrates excellent performance in the task of automatic speech recognition(ASR),but there is still room for improvement in feature extraction.This study identifies two main issues with the model:first,it focuses on extracting global feature interactions,overlooking other useful features such as local feature interactions;second,it does not fully utilize low-level feature interactions.To address these issues and enhance the model's performance in ASR tasks,we propose a Convolutional Linear Mapping(CMLP)module to enhance local feature interactions and a Low-level Feature Fusion(LF)module to integrate high-level and low-level features.By integrating these modules,we construct the CLformer model.Experimental results on two Chinese Mandarin datasets(Aishell-1 and HKUST)demonstrate that CLformer significantly improves model performance:by 0.3%on Aishell-1 and 0.5%on HKUST compared to the baseline.This validates the effectiveness of our optimization strategy.
Keywords：Transformer modelautomatic speech recognitionfeature fusionlocal featureglobal feature
Publication Date：2024-05-30
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：8( 27-34 )