Excitation Features of Speech for Speaker-Specific Emotion Detection

Sudarsana Reddy Kadiri*, Paavo Alku

*Corresponding author for this work

Research output: Contribution to journalArticleScientificpeer-review

1 Citation (Scopus)
21 Downloads (Pure)


In this article, we study emotion detection from speech in a speaker-specific scenario. By parameterizing the excitation component of voiced speech, the study explores deviations between emotional speech (e.g., speech produced in anger, happiness, sadness, etc.) and neutral speech (i.e., non-emotional) to develop an automatic emotion detection system. The excitation features used in this study are the instantaneous fundamental frequency, the strength of excitation and the energy of excitation. The Kullback-Leibler (KL) distance is computed to measure the similarity between feature distributions of emotional and neutral speech. Based on the KL distance value between a test utterance and an utterance produced in a neutral state by the same speaker, a detection decision is made by the system. In the training of the proposed system, only three neutral utterances produced by the speaker were used, unlike in most existing emotion recognition and detection systems that call for large amounts of training data (both emotional and neutral) by several speakers. In addition, the proposed system is independent of language or lexical content. The system is evaluated using two databases of emotional speech. The performance of the proposed detection method is shown to be better than that of reference methods.

Original languageEnglish
Article number9046041
Pages (from-to)60382-60391
Number of pages10
JournalIEEE Access
Publication statusPublished - 1 Jan 2020
MoE publication typeA1 Journal article-refereed


  • emotion detection
  • excitation source
  • Kullback-Leibler (KL) distance
  • linear prediction (LP) analysis
  • paralinguistics
  • Speech analysis
  • zero frequency filtering (ZFF)


Dive into the research topics of 'Excitation Features of Speech for Speaker-Specific Emotion Detection'. Together they form a unique fingerprint.

Cite this