Automatic Speech Emotion Recognition using Support Vector Machine

Shen, Peipei; Zhou, Changjun; Chen, Xiong

doi:10.1109/emeit.2011.6023178

Cited by 133 publications

(61 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SVM classifiers are mainly based on the use of kernel functions to nonlinearly map the original features to a high dimensional space where data can be well classified using a linear classifier. SVM classifiers are widely used in many pattern recognition applications and shown to outperform other well-known classifiers [8]. SVM has shown to have better generalization performance than traditional techniques in solving classification problems.…”

Section: Classifier Selectionmentioning

confidence: 99%

See 1 more Smart Citation

Speech Emotion Recognition: A Review

Joshi¹,

Zalte²

2013

IOSR-JECE

View full text Add to dashboard Cite

Section: Classifier Selectionmentioning

confidence: 99%

“…Mel frequency scale is the most widely used feature of the speech, with a simple calculation, good ability of the distinction, anti-noise and other advantages [8]. By employing feature extraction technique number of features can be extracted from the emotional speech.…”

Section: Mel-frequency Cepstrum Coefficients (Mfcc)mentioning

confidence: 99%

Speech Emotion Recognition: A Review

Joshi¹,

Zalte²

2013

IOSR-JECE

View full text Add to dashboard Cite

“….Pitch has psycho acoustical sound attribute rather than objective physical property and can be measured as frequency.  Intensity: Intensity is used to encode prosodic information and shows emotion of spoken utterance in term of energy of speech signal which depend on short term energy and short term average amplitude [16]. Energy of speech signal affected by stimulation level of emotions, due to which intensity can be used in the field of emotion recognition [17].…”

Section: Prosodic Features and Learning Classifiersmentioning

confidence: 99%

“…Prosodic features are treated as major correlates of vocal emotion for discriminating and identifying the emotion from spoken utterances and emotion present in daily life conversation respectively [11]. Speaker emotional state can be indicated by prosodic features, some of the significant prosodic features used to recognize emotion from speech utterances are energy, speech rate, pitch, duration, intensity, formant, Mel frequency cepstrum coefficient (MFCC) and linear prediction cepstrum coefficient (LPCC) [12,13,14] Three prosodic features (intensity, pitch and formant) with the possible combinations of features with and without pitch were used in this experimental framework to analyzing the impact of pitch on learning classifiers.  Pitch: One of the important perceptual property based prosody features used to detect emotion from spoken utterances are called pitch or glottal wave form.…”

Section: Prosodic Features and Learning Classifiersmentioning

confidence: 99%

Analyzing the Impact of Prosodic Feature (Pitch) on Learning Classifiers for Speech Emotion Corpus

Ali¹,

Khan²,

Bashir³

2015

IJITCS

View full text Add to dashboard Cite

Abstract-Emotion plays a significant role in human perception and decision making whereas, prosodic features plays a crucial role in recognizing the emotion from speech utterance. This paper introduces the speech emotion corpus recorded in the provincial languages of Pakistan: Urdu, Balochi, Pashto Sindhi and Punjabi having four different emotions (Anger, Happiness, Neutral and Sad). The objective of this paper is to analyze the impact of prosodic feature (pitch) on learning classifiers (adaboostM1, classification via regression, decision stump, J48) in comparison with other prosodic features (intensity and formant) in term of classification accuracy using speech emotion corpus recorded in the provincial languages of Pakistan. Experimental framework evaluated four different classifiers with the possible combinations of prosodic features with and without pitch. An experimental study shows that the prosodic feature (pitch) plays a vital role in providing the significant classification accuracy as compared to prosodic features excluding pitch. The classification accuracy for formant and intensity either individually or with any combination excluding pitch are found to be approximately 20%. Whereas, pitch gives classification accuracy of around 40%.

show abstract

“…It is used for formant analysis [8]. LPC is one of the most powerful speech analysis techniques and it has gained popularity as a formant estimation technique [9].…”

Section: Formantsmentioning

confidence: 99%