東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Spectral analysis methods for automa...

Parinam, Venkata Neelima Devi.

FindBook

Google Book

Amazon

博客來

Spectral analysis methods for automatic speech recognition applications.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Spectral analysis methods for automatic speech recognition applications./
作者:	Parinam, Venkata Neelima Devi.
面頁冊數:	97 p.
附註:	Source: Masters Abstracts International, Volume: 52-02.
Contained By:	Masters Abstracts International52-02(E).
標題:	Engineering, Electronics and Electrical. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=1543636
ISBN:	9781303310423

Spectral analysis methods for automatic speech recognition applications.
Parinam, Venkata Neelima Devi.

Spectral analysis methods for automatic speech recognition applications. - 97 p.

Source: Masters Abstracts International, Volume: 52-02.

Thesis (M.S.)--State University of New York at Binghamton, 2013.

In this thesis, we evaluate the front-end of Automatic Speech Recognition (ASR) systems, with respect to different types of spectral processing methods that are extensively used. A filter bank approach for front end spectral analysis is one of the common methods used for spectral analysis. In this work we describe and evaluate spectral analysis based on Mel and Gammatone filter banks. These filtering methods are derived from auditory models and are thought to have some advantages for automatic speech recognition work. Experimentally, however, we show that direct use of FFT spectral values is just as effective as using either Mel or Gammatone filter banks, provided that the features extracted from the FFT spectral values take into account a Mel or Mel-like frequency scale. It is also shown that trajectory features based on sliding block of spectral features, computed using either FFT or filter bank spectral analysis are considerably more effective, in terms of ASR accuracy, than are delta and delta-delta terms often used for ASR. Although there is no major performance disadvantage to using a filter bank, simplicity of analysis is a reason to eliminate this step in speech processing. These assertions hold for both clean and noisy speech.

ISBN: 9781303310423Subjects--Topical Terms:

626636
Engineering, Electronics and Electrical.

Spectral analysis methods for automatic speech recognition applications.
LDR:02140nam a2200289 4500 001 1965657
005 20141029122146.5
008 150210s2013 ||||||||||||||||| ||eng d
020 $a 9781303310423
035 $a (MiAaPQ)AAI1543636
035 $a AAI1543636
040 $a MiAaPQ $c MiAaPQ
100 1 $a Parinam, Venkata Neelima Devi. $3 2102346
245 1 0 $a Spectral analysis methods for automatic speech recognition applications.
300 $a 97 p.
500 $a Source: Masters Abstracts International, Volume: 52-02.
500 $a Adviser: Stephen A. Zahorian.
502 $a Thesis (M.S.)--State University of New York at Binghamton, 2013.
520 $a In this thesis, we evaluate the front-end of Automatic Speech Recognition (ASR) systems, with respect to different types of spectral processing methods that are extensively used. A filter bank approach for front end spectral analysis is one of the common methods used for spectral analysis. In this work we describe and evaluate spectral analysis based on Mel and Gammatone filter banks. These filtering methods are derived from auditory models and are thought to have some advantages for automatic speech recognition work. Experimentally, however, we show that direct use of FFT spectral values is just as effective as using either Mel or Gammatone filter banks, provided that the features extracted from the FFT spectral values take into account a Mel or Mel-like frequency scale. It is also shown that trajectory features based on sliding block of spectral features, computed using either FFT or filter bank spectral analysis are considerably more effective, in terms of ASR accuracy, than are delta and delta-delta terms often used for ASR. Although there is no major performance disadvantage to using a filter bank, simplicity of analysis is a reason to eliminate this step in speech processing. These assertions hold for both clean and noisy speech.
590 $a School code: 0792.
650 4 $a Engineering, Electronics and Electrical. $3 626636
650 4 $a Physics, Acoustics. $3 1019086
650 4 $a Speech Communication. $3 1017408
690 $a 0544
690 $a 0986
690 $a 0459
710 2 $a State University of New York at Binghamton. $b Electrical Engineering. $3 1057631
773 0 $t Masters Abstracts International $g 52-02(E).
790 $a 0792
791 $a M.S.
792 $a 2013
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=1543636