A speech recognition method with enhanced transformer decoder
Abstract Addressing the issue that the Transformer decoder struggles to capture local features for monotonic alignment in speech recognition, and simultaneously incorporating language model cold fusion training into the decoder, an enhanced decoder-based speech recognition model is investigated. The...
Saved in:
Main Authors: | Hengbo Hu, Tong Niu, Zhenhua He |
---|---|
Format: | Article |
Language: | English |
Published: |
SpringerOpen
2025-02-01
|
Series: | EURASIP Journal on Audio, Speech, and Music Processing |
Subjects: | |
Online Access: | https://doi.org/10.1186/s13636-025-00394-6 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Efficient guided inpainting of larger hole missing images based on hierarchical decoding network
by: Xiucheng Dong, et al.
Published: (2025-01-01) -
AMEEGNet: attention-based multiscale EEGNet for effective motor imagery EEG decoding
by: Xuejian Wu, et al.
Published: (2025-01-01) -
Arabic Speech Recognition Based on Encoder-Decoder Architecture of Transformer
by: Mohanad Sameer, et al.
Published: (2023-03-01) -
Low Complexity Unquantized Forward Stack Decoding Algorithm for Spinal Codes in Measurement While Drilling Communication
by: Xiaoyang Yu, et al.
Published: (2025-01-01) -
Encoding and Decoding of Secret Messages Using Matrices
by: James, Niwagaba
Published: (2022)