遞歸神經網絡在語音辨識上之表現分析

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/79647

Title:	遞歸神經網絡在語音辨識上之表現分析
Authors:	王薏婷;WANG, YI-TING
Contributors:	數學系
Keywords:	語音辨識
Date:	2019-01-25
Issue Date:	2019-04-02 15:10:09 (UTC+8)
Publisher:	國立中央大學
Abstract:	語音辨識是人工智慧相當關注的領域，但受限於不同環境的影響，至今依舊難有一個系統能如人類般清晰的識別。本研究旨在探討梅爾頻率倒譜系數(MFCCs) 及連接性音頻分類(CTC)在語音辨識系統上的功能性。本研究使用github 上所提供的無噪聲語料，以不同的處理方式建構遞歸神經網絡模型，並選定一些變因做為探討比較的對象。;Speech recognition is part of the artificial intelligence that is highly concerned, but is limited by different environmental influences. It is still a difficult subject to have a system that can be clearly identified as humans. This study aims to investigate the functionality of the Mel Frequency Cepstral Coefficients (MFCCs) and the Connectionist Temporal Classification (CTC) on speech recognition systems. This study uses the noise-free corpus provided on github to construct a recursive neural network model in different ways, and selects some variables as the object of discussion and comparison.
Appears in Collections:	[Graduate Institute of Mathematics] Electronic Thesis & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	234	View/Open

社群 sharing