Speech Emotion Recognition

Crossbreed Wavelet decomposition for speech emotion detection using HMM

Five types of emotions were analyzed and compared in previous paper. The proposed method was completely simulated on PC; the results demonstrate that significant advances have been achieved in this area. The wavelet transform and improved HMM make our speech emotion recognition system robust. The combination of wavelet transforms and HMM as a solid model that can reduce error rates.

Table 1. The result using wavelet transform and HMM

Emotion A F J S P

Anger 85 6 1 8 0

Fear 14 78 6 1 1

Joy 0 0 89 1 10

Sadness 1 3 4 92 0

Surprise 0 0 16 4 79

Total 101 87 116 106 90

Table 2. The result using wavelet transforms and improved HMM

Emotion A F J S P

Anger 90 4 1 4 1

Fear 11 83 3 1 2

Joy 0 0 95 2 3

Sadness 0 1 2 97 0

Surprise 0 2 7 3 88

Total 101 90 108 107 94

When compare table 1& 2 there is certain improve in efficiency but many shortages are lying the selecting of the features, so to find more efficient features and to do further analysis and experiment in a wide field.


Keeping problems discussed in previous chapter following will be my goals, which will be achieved during my thesis:

• The emotion is to be detected from the input speech signal the whole signal processing revolves around the speech signal for the extraction and selection of speech features correspond to emotions.

• In the previous work there is only single wavelet is used so to improve efficiency, the crossbreed decomposition takes place.

• The next is generating a database for training and testing of extracted speech features followed by the last stage of emotion detection by the classifier section using pattern recognition algorithms.


• Extraction and selection of speech feature: - The extraction of speech feature involves potential audio segmentation followed by acoustic preprocessing like filtering to form their meaningful units. The purpose of the audio segmentation is to segment a speech signal into units that are representative for emotions

• Database for training and testing: - A good database is as important as the desired result. There are different database created by speech processing community used in research work.

• Detect emotions: - Stored database are classifier to detect the emotions by comparing the vectors from the trained data and test data vector.

Evner: Matlab and Mathematica

Se mere: types of algorithms, the analysis of algorithms, testing algorithms, test algorithms, problems in algorithms, problems.algorithms, efficiency of algorithms, different types of algorithms, data stage 8.1, area vectors, analysis of algorithms, algorithms test, algorithms problems, algorithms efficiency, algorithms and analysis, speech recognition, signal matlab, matlab training, matlab test, matlab signal processing, matlab find, mathematica signal processing, data extraction and input, c++ speech, c speech

Om arbejdsgiveren:
( 0 bedømmelser ) Jammu, India

Projekt ID: #6015704

6 freelancers are bidding on average ₹14283 for this job


A proposal has not yet been provided

₹7368 INR in 3 dage
(39 bedømmelser)

Hello sir, I am a professional freelancer in the field of image processing and communication system . PLease get in touch , I will be able to deliver the results. With regards, N L Ramachandrachudamani

₹13888 INR in 10 dage
(2 bedømmelser)

Hi, I have implemented many signal processing algorithms like Filters, G.7xx, LPC, JPEG, Video Codecs, TCP/IP, Webserver, Ethernet, Security Encryption Algorithms. Ported them on DSPs and MicroControllers too. Flere

₹11111 INR in 10 dage
(2 bedømmelser)

Dear sir, I am very much interested in doing the project. I am an enthusiastic person. I am also pursuing my PHD in emotion detection and the project is quite related to my area (EEG based emotion detection). The poi Flere

₹7777 INR in 3 dage
(1 bedømmelse)

I am a writer and teacher with a postgradue degree (PhD and MBA) in the area of research.I am a full time freelancer after work in academia for more than 15 years who has taught in all levels of education and I am will Flere

₹25263 INR in 3 dage
(0 bedømmelser)

i will do this project based on mathematica. using mathematica are lot of easier than any software. can you repeat your main object why you are using this paper for your thesis?

₹33333 INR in 30 dage
(0 bedømmelser)

Experience on making projects on DWT, DTDCT, DCT. Completed [url removed, login to view], M.E. projects successfully on local market.

₹12222 INR in 8 dage
(0 bedømmelser)