A motion-based approach for audio-visual automatic speech recognition

The research work presented in this thesis introduces novel approaches for both visual region of interest extraction and visual feature extraction for use in audio-visual automatic speech recognition. In particular, the speaker‘s movement that occurs during speech is used to isolate the mouth region...

Full description

Saved in:
Bibliographic Details
Main Author: Nasir Ahmad
Format: Default Thesis
Published: 2019
Subjects:
Mechanical engineering not elsewhere classified
Automatic speech recognition (ASR)
Audio-visual automatic speech recognition (AVASR)
Bi-modal speech recognition
Visual front-end
Features extraction
Visual ROI
Speech dynamics
Mechanical Engineering not elsewhere classified
Online Access:https://hdl.handle.net/2134/8564
Tags: Add Tag
No Tags, Be the first to tag this record!

Similar Items