| DC 欄位 |
值 |
語言 |
| DC.contributor | 電機工程學系 | zh_TW |
| DC.creator | 郭又禎 | zh_TW |
| DC.creator | Yo-zhen Kuo | en_US |
| dc.date.accessioned | 2014-7-15T07:39:07Z | |
| dc.date.available | 2014-7-15T07:39:07Z | |
| dc.date.issued | 2014 | |
| dc.identifier.uri | http://ir.lib.ncu.edu.tw:88/thesis/view_etd.asp?URN=101521062 | |
| dc.contributor.department | 電機工程學系 | zh_TW |
| DC.description | 國立中央大學 | zh_TW |
| DC.description | National Central University | en_US |
| dc.description.abstract | 在語音辨識系統中，梅爾倒頻譜係數(Mel frequency cepstral coefficients, MFCCs)為常用的特徵值參數，然而隨著MFCC被廣泛地應用，許多研究MFCC改良的方法也被提出，本論文針對三角帶通濾波器能量組進行權重調整，以粒子群演算法尋找濾波器組的最佳權重，演算法中以語料能量統計曲線與濾波器組包絡線曲線之差作為適應函數，使濾波器組更能符合人耳感受度，以提升辨識效果。由實驗結果得知，改良後的MFCC的辨識效果優於傳統MFCC，且其抗高頻雜訊能力也優於傳統MFCC。 | zh_TW |
| dc.description.abstract | In the speech recognition system, Mel frequency cepstral coefficients (MFCCs) are the feature parameters that are used widely. Because of the wide applications of MFCC in the audio signal processing, lots of studies on the improvement of MFCCs were presented. In this study, we use particle swarm optimization algorithm to optimize the weight of MFCC filter bank. We utilize the difference between voice training database’s energy statistical curve and MFCC filter bank’s envelope as fitness function. Experimental results show that the proposed MFCCs method improves the recognition rate. In noisy environment experiments, the presented MFCCs method also improves the recognition performance. | en_US |
| DC.subject | 梅爾倒頻譜系數 | zh_TW |
| DC.subject | 粒子群演算法 | zh_TW |
| DC.subject | 關鍵詞萃取 | zh_TW |
| DC.subject | MFCC | en_US |
| DC.subject | PSO | en_US |
| DC.subject | keyword spotting | en_US |
| DC.title | 改良式梅爾倒頻譜參數應用於關鍵字萃取 | zh_TW |
| dc.language.iso | zh-TW | zh-TW |
| DC.title | Improved Mel-scale Frequency Cepstral Coefficients for Keyword Spotting Technique | en_US |
| DC.type | 博碩士論文 | zh_TW |
| DC.type | thesis | en_US |
| DC.publisher | National Central University | en_US |