Upgrading the Performance of Speech Emotion Recognition at the Segmental Level
Journal Title: IOSR Journals (IOSR Journal of Computer Engineering) - Year 2013, Vol 15, Issue 3
Abstract
This paper presents an efficient approach for maximizing the accuracy of automatic speech emotion recognition in English, using minimal inputs, minimal features, lesser algorithmic complexity and reduced processing time. Whereas the findings reported here are based on the exclusive use of vowel formants, most of the related previous works used tens or even hundreds of other features. In spite of using a greater level of signal processing, the recognition accuracy reported earlier was often lesser than that obtained by our approach. This method is based on vowel utterances and the first step comprises statistical pre-processing of the vowel formants. This is followed by the identification of the best formants using the KMeans, K-nearest neighbor and Naive Bayes classifiers. The Artificial neural network that was used for the final classification gave an accuracy of 95.6% on elicited emotional speech. Nearly 1500 speech files from ten female speakers in the neutral and six basic emotions were used to prove the efficiency of the proposed approach. Such a result has not been reported earlier for English and is of significance to researchers, sociologists and others interested in speech.
Authors and Affiliations
Agnes Jacob
Keywords
Related Articles
- EP ID EP104707
- DOI -
- Views 107
- Downloads 0
A Cost-Effective Delay Model for Leased Data Centers to Establish Private Cloud Computing Services
Abstract: Nowadays, using of cloud computing services and developing movement towards on-demand and inexpensive communication and storage infrastructures, and also specialized software is one of the main topics for discu...
Progressivism, Modernism and Urdu Literature.A Comparative View
Abstract:The paper seeks to explore the holocaust of partition in the subcontinent after the great political divide erupting from 1946 massacre which produced writers like Bedi, Manto and Khwaja Ahmad Abbas. A modest att...
Improved Text Analysis Approach for Predicting Effects of Nutrient on Human Health using Machine Learning Techniques
Abstract : A text analysis method is introduced which processes the unstructured information from document collection in order to support efficient text classification and information extraction. The Information ex...
Analyzing the Effect of Varying CBR on AODV, DSR, IERP Routing Protocols in MANET
Mobile Ad Hoc Networks (MANET) are wireless networks which do not require any infrastructure support for transferring data packet between two nodes. Mobile ad-hoc network have the attributes such as wireless conn...
Analysis of Digital Image Splicing Detection
Abstract: The availability of photo manipulation software has made it unprecedentedly easy to manipulate images for malicious purposes. One of the most common forms of digital image or photographic manipulation ope...