Spectral Properties and Prosodic Parameters of Emotional Speech in Czech and Slovak

Přibil, Jiří; Přibilová, Anna

doi:10.5772/19369

Cited by 4 publications

(6 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Note the differences in the spectrum for all vowels depending on the emotion. These results are similar to the ones presented in [28]. Thus, the developed speech corpora is representative of the considered emotions and can be used for classification tasks.…”

Section: Speech Corpussupporting

confidence: 86%

See 1 more Smart Citation

Recognition of Emotions in Mexican Spanish Speech: An Approach Based on Acoustic Modelling of Emotion‐Specific Vowels

Caballero‐Morales

2013

The Scientific World Journal

View full text Add to dashboard Cite

An approach for the recognition of emotions in speech is presented. The target language is Mexican Spanish, and for this purpose a speech database was created. The approach consists in the phoneme acoustic modelling of emotion-specific vowels. For this, a standard phoneme-based Automatic Speech Recognition (ASR) system was built with Hidden Markov Models (HMMs), where different phoneme HMMs were built for the consonants and emotion-specific vowels associated with four emotional states (anger, happiness, neutral, sadness). Then, estimation of the emotional state from a spoken sentence is performed by counting the number of emotion-specific vowels found in the ASR's output for the sentence. With this approach, accuracy of 87–100% was achieved for the recognition of emotional state of Mexican Spanish speech.

show abstract

Section: Speech Corpussupporting

confidence: 86%

“…However, most of the emotional speech corpora consider four or six emotions [8]. In this work the following emotions were considered as defined in [25–28]: anger, happiness, neutral, and sadness. The details of the corpus sentences for the emotions and the speech acquisition process are presented in the following section.…”

Section: Speech Corpusmentioning

confidence: 99%

Recognition of Emotions in Mexican Spanish Speech: An Approach Based on Acoustic Modelling of Emotion‐Specific Vowels

Caballero‐Morales

2013

The Scientific World Journal

View full text Add to dashboard Cite

show abstract

“…In our algorithm, the values of the HNR, SC and SFM are obtained only from the voiced speech frames. In the case of the SE parameter, the values are determined from the voiced as well as unvoiced frames with the signal energy higher than the threshold (calculated as e c0 using the first cepstral coefficient) for elimination of speech pauses between words within the sentence and beginning and ending parts of the sentence [26].…”

Section: The Harmonics-to-noise Ratio (Hnr) Provides Anmentioning

confidence: 99%

“…These two languages (belonging to the Slavonic languages) are similar but different, therefore we can use a common speech corpus to obtain spectral parameters, but on the phonetic and prosody level the synthetic speech must be processed separately. In our previous work, we performed statistical analysis and comparison of emotional speech properties for the Czech and Slovak languages using basic spectral features consisting of the first three formant positions together with their bandwidths and formant tilts, complementary spectral features (CSF) (SC, SFM, and SE), and prosodic parameters-fundamental frequency (F0), microintonation, jitter, shimmer [26].…”

Section: Introductionmentioning

confidence: 99%

“…The article describes performed experiments and comparison of GMM classification of male and female acted speech in four emotional states (joy, sadness, anger, and a neutral state) spoken in Czech and Slovak. This speech corpus was primarily used for determination of spectral and prosodic parameters for emotional speech conversion [26]. This article is also aimed to verify a functionality of the proposed GMM emotional speech classifier structure including the stability of the obtained results, to perform an analysis of influence of setting of parameters for GMM training process (number of used mixture components and used number of iterations), and above all, to investigate the influence of different types of used speech features (spectral and/or supra-segmental).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Evaluation of influence of spectral and prosodic features on GMM classification of Czech and Slovak emotional speech

Přibil

Přibilová²

2013

J AUDIO SPEECH MUSIC PROC.

View full text Add to dashboard Cite

This article analyzes and compares influence of different types of spectral and prosodic features for Czech and Slovak emotional speech classification based on Gaussian mixture models (GMM). Influence of initial setting of parameters (number of mixture components and used number of iterations) for GMM training process was analyzed, too. Subsequently, analysis was performed to find how correctness of emotion classification depends on the number and the order of the parameters in the input feature vector and on the computation complexity. Another test was carried out to verify the functionality of the proposed two-level architecture comprising the gender recognizer and of the emotional speech classifier. Next tests were realized to find dependence of some negative aspect (processing of the input speech signal with too short time duration, the gender of a speaker incorrectly determined, etc.) on the stability of the results generated during the GMM classification process. Evaluations and tests were realized with the speech material in the form of sentences of male and female speakers expressing four emotional states (joy, sadness, anger, and a neutral state) in Czech and Slovak languages. In addition, a comparative experiment using the speech data corpus in other language (German) was performed. The mean classification error rate of the whole classifier structure achieves about 21% for all four emotions and both genders, and the best obtained error rate was 3.5% for the sadness style of the female gender. These values are acceptable in this first stage of development of the GMM classifier. On the other hand, the test showed the principal importance of correct classification of the speaker gender in the first level, which has heavy influence on the resulting recognition score of the emotion classification. This GMM classifier should be used for evaluation of the synthetic speech quality after applied voice conversion and emotional speech style transformation.

show abstract

SVM-Based Detection of Misannotated Words in Read Speech Corpora

Matoušek

Tihelka

2013

Text, Speech, and Dialogue

View full text Add to dashboard Cite

Spectral Properties and Prosodic Parameters of Emotional Speech in Czech and Slovak

Cited by 4 publications

References 20 publications

Recognition of Emotions in Mexican Spanish Speech: An Approach Based on Acoustic Modelling of Emotion‐Specific Vowels

Recognition of Emotions in Mexican Spanish Speech: An Approach Based on Acoustic Modelling of Emotion‐Specific Vowels

Evaluation of influence of spectral and prosodic features on GMM classification of Czech and Slovak emotional speech

SVM-Based Detection of Misannotated Words in Read Speech Corpora

Contact Info

Product

Resources

About