Speech Recognition System using MATLAB: Design, Implementation, and Samples Codes (Paperback)

Ahmad A. M. Abushariah, Teddy Surya Gunawan

  • 出版商: LAP LAMBERT
  • 出版日期: 2011-09-16
  • 售價: $2,070
  • 貴賓價: 9.5$1,967
  • 語言: 英文
  • 頁數: 112
  • 裝訂: Paperback
  • ISBN: 3846503762
  • ISBN-13: 9783846503768
  • 相關分類: Matlab語音辨識 Speech-recognition
  • 海外代購書籍(需單獨結帳)

買這商品的人也買了...

商品描述

Research in automatic speech recognition has been done for almost four decades. This project aims to develop automated English digits speech recognition system using Matlab. The system is able to recognize the spoken utterances by translating the speech waveform into a set of feature vectors using Mel Frequency Cepstral Coefficients (MFCC) technique, which then estimates the observation likelihood by using the Forward algorithm. The Hidden Markov Model (HMM) parameters are estimated by applying the Baum-Welch algorithm on previously trained samples. The most likely sequence is then decoded using Viterbi algorithm, thus producing the recognized word. This project focuses on all English digits from (Zero through Nine), which is based on isolated words structure. Two modules were developed, namely the isolated words speech recognition and the continuous speech recognition. Both modules were tested in both clean and noisy environments and showed relatively sucessful recognition rates. The samples of Matlab codes were provided in the Appendix.

商品描述(中文翻譯)

自動語音識別的研究已經進行了近四十年。本項目旨在使用Matlab開發自動英文數字語音識別系統。該系統能夠通過將語音波形轉換為一組特徵向量,使用Mel頻率倒谱係數(MFCC)技術來識別口語表達,然後使用前向算法估計觀察概率。隱馬爾可夫模型(HMM)參數通過在先前訓練的樣本上應用Baum-Welch算法來估計。然後使用Viterbi算法解碼最可能的序列,從而產生識別的單詞。本項目專注於所有英文數字(從零到九),基於孤立詞結構。開發了兩個模塊,即孤立詞語音識別和連續語音識別。這兩個模塊在乾淨和嘈雜的環境中進行了測試,並顯示出相對成功的識別率。附錄中提供了Matlab代碼的示例。