2008/11/01 by Aditya Bihar Kandali, Aurobinda Routray, T.K. Basu · 2 citations
Health Professions · Computer Science · #Infant Health and Development #Speech Recognition and Synthesis #Speech and Audio Processing #Assamese #Mel-frequency cepstrum #Speech recognition #Mixture model #Computer science #Classifier (UML) #Artificial intelligence #Speaker recognition #Pattern recognition (psychology) #Sentence #Emotion recognition #Feature extraction #Natural language processing #Linguistics
paper · doi:10.1109/tencon.2008.4766487
openalex publication_date 2008/11/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/29
This paper presents a method based on Gaussian mixture model (GMM) classifier and Mel-frequency cepstral coefficients (MFCC) as features for emotion recognition from Assamese speeches. For training and testing of the method, data collection is carried out in Jorhat (Assam, India), which consisted of acted speeches of one short emotionally biased sentence repeated 5 times with different styles by 27 speakers (14 Male and 13 female) for training and one long emotional speech by each speaker for testing. The experiments are performed for the cases of (i) text-independent but speaker-dependent and (ii) text-independent and speaker-independent.