Emotion Recognition From Speech
Using In-Depth Analysis Of Glottal And Prosodic Features, Various Classifiers, Speech Corpora And Noise Conditions
Versandkostenfrei!
Versandfertig in 6-10 Tagen
44,99 €
inkl. MwSt.
PAYBACK Punkte
22 °P sammeln!
Emotion recognition from speech has received considerable attention in recent years. Fields like homeland security, remote monitoring of patients, improved communication for people with disabilities, and even closed captioning can greatly benefit from advances in the area. This book reveals some of the leading techniques in spoken emotion recognition and provides an in-depth analysis and comparison of key methodologies in the field. The reader is first introduced to some of the most important aspects of spoken emotion recognition. The author then reveals new feature domains, novel recognition ...
Emotion recognition from speech has received considerable attention in recent years. Fields like homeland security, remote monitoring of patients, improved communication for people with disabilities, and even closed captioning can greatly benefit from advances in the area. This book reveals some of the leading techniques in spoken emotion recognition and provides an in-depth analysis and comparison of key methodologies in the field. The reader is first introduced to some of the most important aspects of spoken emotion recognition. The author then reveals new feature domains, novel recognition methods and various feature extraction techniques all tested across different speech corpora. This work also reveals new emotion classification techniques and compares their recognition performance to some classical emotion recognition methods. In addition, all methods are tested in different real-world noisy conditions to compare their robustness. This is part of an effort to bring the scientific advancement in the field closer to the real-world product environment. In these terms this book constitutes a significant advancement in the area of emotion recognition from speech.
Andere Kunden interessierten sich für
