Expression of basic emotions in Estonian parametric text-to-speech synthesis

Tamuri, Kairi; Mihkla, Meelis

doi:10.12697/jeful.2015.6.3.06

Cited by 3 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Korpuse materjali põhjal on tehtud uurimusi emotsioonide akustikast (Pajupuu, H. & Pajupuu et al 2015), kuulaja vanuse ja empaatia ning kultuuri ja keele osatähtsusest emotsioonide äratundmisel (Altrov & Pajupuu 2010;Altrov & Pajupuu 2015;Altrov & Pajupuu et al 2013). Korpust on kasutatud ka emotsionaalse kõne sünteesiks (Tamuri & Mihkla 2015) ning emotsioonide automaatse tuvastuse ühe treeningbaasina 1 . Kui emotsionaalse kõne korpuse materjal on kasutatav pigem kuulaja emotsioonitaju mõjutavate tegurite uurimiseks, siis kõneleja omaduste ja seisundite uurimiseks on vaja teistsuguse materjali ja märgendusega korpust.…”

Section: Aastaunclassified

Arvutiparalingvistika väljakutsed ja eesti hääle meeldivus

Pajupuu

Pajupuu²,

Altrov³

2017

View full text Add to dashboard Cite

Teesid: Artiklis heidetakse pilk viimase kümnendi suundumustele arvutiparalingvistikas: kõneleja omaduste ja seisundite tuvastamisele häälest ning nõuetest sellega seonduvatele kõnekorpustele. Tutvustatakse Eesti häälekorpuse olemust ning võimalust hääle meeldivust akustiliselt iseloomustada ja automaatselt tuvastada, kasutades Genfi minimaalset akustiliste parameetrite laiendatud kogumit eGeMAPS. Märksõnad: arvutiparalingvistika, eGeMAPS, häälekorpus, hääle meeldivus, kõneakustikaViimasel kümnendil on kõneuurimises toimunud suured muutused. Selle taga on eeskätt rahastuse ja arvutivõimsuse kasv (suurt hulka kõnet on võimalik töödelda tuhandetes kordades kiiremini kui varem). Ka on kõneuurimisel selged rakenduslikud eesmärgid. Suured firmad, nagu Google, Microsoft ja IBM on panustanud palju ressurssi kõnetöötluse tarkvarasse, ja mis oluline, palju sellest on kättesaadav vabavarana. Kõnetuvastuse ja kõnesünteesi ühisraken-duse heaks näiteks on Skype'i tõlkemoodul. Skype'i teel vesteldes on võimalik peaaegu reaalajas kõnet tõlkida kaheksasse keelde (inglise, prantsuse, saksa, hiina, itaalia, hispaania, portugali, araabia, vene

show abstract

Section: Aastaunclassified

Arvutiparalingvistika väljakutsed ja eesti hääle meeldivus

Pajupuu

Pajupuu²,

Altrov³

2017

View full text Add to dashboard Cite

show abstract

“…The selection of the appropriate acoustic model for a text to be voiced requires information on the affectivity of the text (see Tamuri & Mihkla 2015).…”

Section: Identifying Polarity In Different Text Typesmentioning

confidence: 99%

Identifying Polarity in Different Text Types

Pajupuu¹,

Altrov²,

Pajupuu³

2016

FEJF

View full text Add to dashboard Cite

While Sentiment Analysis aims to identify the writer's attitude toward individuals, events or topics, our aim is to predict the possible effect of a written text on the reader. For this purpose, we created an automatic identifier of the polarity of Estonian texts, which is independent of domain and of text type. Depending on the approach chosen -lexicon-based or machine learning -the identifier uses either a lexicon of words with a positive or negative connotation, or a text corpus where orthographic paragraphs have been annotated as positive, negative, neutral or mixed. Both approaches worked well, resulting in a nearly 75% accuracy on average. It was found that in some cases the results depend on the text type, notably, with sports texts the lexicon-based approach yielded a maximum accuracy of 80.3%, while over 88% was gained for opinion stories approached by machine learning.

show abstract

“…Otherwise, if language-dependent features are used, the system has to be changed every time in order to tailor it to the specifications of the language of the database. The features that have been used in the recently published research are pitch, intensity [21], formants [22], mel-frequency cepstral coefficients (MFCCs) [23] and filter bank energies (FBE) [24]. The majority of previous studies have exploited different types of features and classifiers.…”

Section: Introductionmentioning

confidence: 99%

A Study of Language and Classifier-independent Feature Analysis for Vocal Emotion Recognition

Noroozi,

Marjanovic,

Njegus

et al. 2018

Preprint

View full text Add to dashboard Cite

Every speech signal carries implicit information about the emotions, which can be extracted by speech processing methods. In this paper, we propose an algorithm for extracting features that are independent from the spoken language and the classification method to have comparatively good recognition performance on different languages independent from the employed classification methods. The proposed algorithm is composed of three stages. In the first stage, we propose a feature ranking method analyzing the state-of-the-art voice quality features. In the second stage, we propose a method for finding the subset of the common features for each language and classifier. In the third stage, we compare our approach with the recognition rate of the state-of-the-art filter methods. We use three databases with different languages, namely, Polish, Serbian and English. Also three different classifiers, namely, nearest neighbour, support vector machine and gradient descent neural network, are employed. It is shown that our method for selecting the most significant language-independent and method-independent features in many cases outperforms state-of-the-art filter methods.

show abstract

Expression of basic emotions in Estonian parametric text-to-speech synthesis

Cited by 3 publications

References 13 publications

Arvutiparalingvistika väljakutsed ja eesti hääle meeldivus

Arvutiparalingvistika väljakutsed ja eesti hääle meeldivus

Identifying Polarity in Different Text Types

A Study of Language and Classifier-independent Feature Analysis for Vocal Emotion Recognition

Contact Info

Product

Resources

About