Statistical characteristics of the formants of the Romanian vowels in emotional states

Zbancioc, Marius Dan; Teodorescu, Horia-Nicolai; Feraru, Monica

doi:10.1109/sped.2011.5940725

Cited by 8 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the present research we used records from the SRoL [10] and [11] database, this being the practical foundation of several similar thematic studies [6], [7] and [8] that have been previously published. The files had a sampling frequency of 24 kHz, which allowed for greater accuracy in extracting the relevant parameters for subsequent statistical processing.…”

Section: Methodsmentioning

confidence: 99%

“…Moreover, [3] summarizes the theoretical contributions regarding the most common normalization procedures used for vowel formants. In the case of the Romanian language, the first studies of this nature have been carried out recently, having all been published in the last decade [4], [5], [6]. To date, some of the results [7] have showed that there are no significant differences between the correlation level of the formants for the vowels of the Romanian language in the case of female participants compared to male participants.…”

Section: Introductionmentioning

confidence: 99%

“…A similar study [6] analyzed the extent to which changes in the variations of formants occur when the speaker's voice is associated to one of the following three fundamental emotions: joy, sadness and anger compared to emotionally neutral speech. The results obtained by applying the CORR function and calculating the linear regression coefficient [6] have led us to the following conclusions: 1) there were no significant changes to the F4 formant depending on the emotions expressed by the speakers; 2) F0 (pitch) had significantly higher values for joy, regarding all vowels; 3) in what sadness is concerned, we observed a slight decrease in fundamental frequency values. The results of a more recent study [9] have shown that, regarding the emotionally neutral speech, the third formant (F3) is largely determined by the correlation of inferior formants (F1 and F2).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Correlations of the Vowel Formants in Romanian and Emotional Effects on Formants

Gheltu¹

2019

2019 International Conference on Applied Electronics (AE)

View full text Add to dashboard Cite

We have investigated the influence of emotions on the level of correlation of the vowel formants in the Romanian language during dynamic pronunciation. We have used in the analysis the sentence /vine mama/ (mother is coming), which is a commonly used phrase in the daily speech, and we have followed the variations of the vowel correlation, depending on the expressed emotion (joy, sadness, anger and emotional neutrality). The main conclusion that we have drawn is that, regarding emotions with negative valence (sadness and anger), the higher order formants (F3 and F4) show a significantly higher correlation level compared to lower order formants (F1 and F2). Moreover, we have found that the variation of the correlation level of the pairs of formants is more homogeneous when emotional neutrality is expressed.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Correlations of the Vowel Formants in Romanian and Emotional Effects on Formants

Gheltu¹

2019

2019 International Conference on Applied Electronics (AE)

View full text Add to dashboard Cite

show abstract

“…Previous results showed that pitch tends to be slightly decreased when speakers express sadness and, for male speakers, it is more difficult to differentiate between sadness and neutral tone for the following vowels: /e/, /i/, /a/ and /ă/ (Zbancioc et al, 2011). Furthermore, sadness is more easily distinguishable from joy and anger compared to neutral tone (Teodorescu and Feraru, 2007).…”

Section: Introductionmentioning

confidence: 92%

The Use of Formants’ Correlation in Assessing the Sadness State of the Speakers

Ghelţu

2022

Bulletin of the Polytechnic Institute of Iași. Electrical Engineering, Power Engineering, Electronics Section

View full text Add to dashboard Cite

The purpose of this study is to further the comparative analysis of the variations in the correlation coefficients of the formants for the Romanian vowels during emotional speech. We created an annotated speech database composed of recordings of speakers pronouncing the following sentences: /vine mama/ (/mother is coming/), /aseară/ (/last night/), /cine a făcut asta/ (/who did this/), first on a neutral tone of voice, and then expressing sadness. The analysis focuses on the influence that sadness has on the vocal signal. The formants and F0 (pitch) of each vowel were extracted. Statistical analysis techniques were applied in order to verify whether the variation of the correlation coefficients between F0 and F1-F4 presents significant variations or whether it tends to be homogenous under the following conditions: (1) same speaker – same vowel – different sentences; (2) same speaker – same vowel – emotional neutrality vs. sadness; (3) different speakers – same sentence – same vowel.

show abstract

Speech emotion recognition for SROL database using weighted KNN algorithm

Feraru

Zbancioc

2013

Proceedings of the International Conference on ELECTRONICS, COMPUTERS and ARTIFICIAL INTELLIGENCE - ECAI-2013

View full text Add to dashboard Cite

In this study, we utilized an improved version of the classical KNN algorithm which associates to each parameter from the features vectors weights according to their performance in the classification process. We obtained the recognition percents of emotions around 65-67%, for the Romanian language, on the SROL database, which are comparable with the results for other languages, with non-professional voice database. This is the first study when the parameters are extracted on the sentence level. Until now, the analysis was made on the phoneme level.

show abstract

Statistical characteristics of the formants of the Romanian vowels in emotional states

Cited by 8 publications

References 13 publications

Correlations of the Vowel Formants in Romanian and Emotional Effects on Formants

Correlations of the Vowel Formants in Romanian and Emotional Effects on Formants

The Use of Formants’ Correlation in Assessing the Sadness State of the Speakers

Speech emotion recognition for SROL database using weighted KNN algorithm

Contact Info

Product

Resources

About