Effect of Compression on Speech Recognition - Saleem, Nasir
23,99 €
inkl. MwSt.

Versandfertig in 6-10 Tagen
payback
12 °P sammeln
  • Broschiertes Buch

This book examined the influence of the speech compression techniques on the Human speech recognition accuracy in noise-free and noisy environments. Five different speech compression techniques including Linear Predictive Coding (LPC), Code Excited Linear Prediction (CELP), Mixed Excited Linear Prediction (MELP), Conjugate Structure-Algebraic Code Excited Linear Prediction (CS-ACELP) and Algebraic Code Excited Linear Prediction (ACELP) were used to measure the speech quality and speech recognition accuracy. The Human Speech Recognition tests were conducted to evaluate the recognition accuracy,…mehr

Andere Kunden interessierten sich auch für
Produktbeschreibung
This book examined the influence of the speech compression techniques on the Human speech recognition accuracy in noise-free and noisy environments. Five different speech compression techniques including Linear Predictive Coding (LPC), Code Excited Linear Prediction (CELP), Mixed Excited Linear Prediction (MELP), Conjugate Structure-Algebraic Code Excited Linear Prediction (CS-ACELP) and Algebraic Code Excited Linear Prediction (ACELP) were used to measure the speech quality and speech recognition accuracy. The Human Speech Recognition tests were conducted to evaluate the recognition accuracy, in noisy and noise-free conditions. The results revealed that Human recognition accuracy remained significant in noise free environments for all speech compression techniques; however, in presence of background noise, the accuracy of speech compression techniques was reduced drastically. It is recommended that noise must be reduced before compressing the speech to improve the recognition accuracy.
Autorenporträt
Engr. Nasir Saleem - Asst. Prof. in Department of Electrical Engineering, Gomal University. Received the B.S degree in Telecommunication Engineering and M.S degree in Electrical Engineering. His research interests are in the area of digital signal processing, speech processing and speech enhancement.