Time filter

Source Type

Nurk T.,Institute of the Estonian Language
Frontiers in Artificial Intelligence and Applications

The article describes the creation of Hidden Markov Model based speech models for both male and female voice for Estonian text-to-speech synthesis. A brief overview of text-to-speech synthesis process is given, focusing on statistical parametric synthesis in particular. System HTS is employed to generate voice models. The creation of speech corpus of Institute of the Estonian Language is analyzed. The process of adapting Estonian-related training data and linguistic specification to HTS is described, as well as experiments carried out on data from different speakers, subcorpora and linguistic specifications. The findings from speech model evaluation are given and possible courses of action to improve the quality of HMM-based speech models trained are proposed. © 2012 The Authors and IOS Press. Source

Tamuri K.,Institute of the Estonian Language
Frontiers in Artificial Intelligence and Applications

Currently the Estonian Emotional Speech Corpus is investigated for the distinctive acoustic parameters of three emotions-anger, joy and sadness-and neutral speech, with a view to recognizable synthesis of emotions in Estonian speech. This article is focused on intensity as one of the parameters vital for emotion synthesis. The research question is whether the intensity of Estonian read speech is in any way affected by emotions. The Estonian Emotional Speech Corpus was used as the acoustic basis of the study. The intensity analysis comprised calculations of the means and ranges of the intensities of emotional and neutral speech. In addition, pairwise studies were applied to find out whether intensity differs across emotions and in comparison with neutral speech in utterance-initial and utterance-final positions. The results revealed that mean intensities make a significant difference between concrete emotions as well as in comparison with neutral speech. The highest intensity was measured in neutral speech and the lowest in the utterances of sadness. Intensity ranges, however, were not significantly different between the utterance groups analysed. Intensity at the beginning and end of utterance was also the highest in neutral speech and the lowest with sadness. Those two groups displayed the only statistically significant differences between the intensities of utterance beginnings as well as ends. © 2012 The Authors and IOS Press. Source

Viikberg J.,Institute of the Estonian Language
Keel ja Kirjandus

In most countries a tip or gratuity (Est. 'jootraha') is an extra amount of money given to someone as a reward for good service. Usually the sum is small and goes straight to the attendant (waiter, taxi driver, hairdresser). In Estonian the word (in the form of yotoraa) was first recorded in the 16 th century and is a loan translation from Low German (cf. drink-, drinke-gelt 'Trinkgeld'). Initially the word was used in the sense of a sacrifice (drink offering) to house fairies, but later it acquired the meaning of extra money given to the attendant for buying himself a drink. As beer was a customary drink at that time, we may very well call the extra allowance beer money. The Low German loan translation jooduraha can be related to an earlier Estonian word joot (PL usu. joodud) that meant offering food and drink to guests on some family occasion (christening, wedding) or celebrating the completion of a major work (e.g. the building of a boat or a windmill). We can find examples in the folk tradition that jootu joodi ('a drink was had') also to ensure the success of a forthcoming undertaking (seal hunting, letting the cattle out for the first time in spring). By the 19th century the word jooduraha had basically acquired the meaning of a reward to someone (errand boy, postman, coachman) in return for a service. The word jootraha first appeared in dictionaries in 1917. Today (young) Estonians often use the word tipp (< English tip) instead of jootraha. Source

Mihkla M.,Institute of the Estonian Language | Hein I.,Institute of the Estonian Language | Kiissel I.,Institute of the Estonian Language | Rapp A.,North Estonian Association of the Blind
Frontiers in Artificial Intelligence and Applications

Systems for automatic reading and broadcasting subtitles (spoken subtitles) are meant to eliminate the language barrier that TV-viewers with special needs (such as the visually handicapped and the dyslectics) may experience in watching TV films or broadcasts in foreign languages that are provided with subtitles. In such systems, a speech signal synchronised with TV subtitles is generated through a separate audio channel. The present article focuses on the questions that have arisen during the development and application of the system of spoken subtitles for Estonian Public Broadcasting: selection of a TTS system and of a synthetic voice, synchronization between the subtitles and synthetic speech utterances, and the marking of speaking turns. Such subjects as the editor interface of the system for automatic reading and broadcasting subtitles as well as the foreign names pronunciation database are also included. © 2014 The Authors and IOS Press. Source

Bimler D.,Massey University | Uuskula M.,Institute of the Estonian Language
Journal of the Optical Society of America A: Optics and Image Science, and Vision

Cross-cultural comparisons of color perception and cognition often feature versions of the "similarity sorting" procedure. By interpreting the assignment of two color samples to different groups as an indication that the dissimilarity between them exceeds some threshold, sorting data can be regarded as low-resolution similarity judgments. Here we analyze sorting data from speakers of Italian, Russian, and English, applying multidimensional scaling to delineate the boundaries between perceptual categories while highlighting differences between the three populations. Stimuli were 55 color swatches, predominantly from the blue region. Results suggest that at least two Italian words for "blue" are basic, a similar situation to Russian, in contrast to English where a single "blue" term is basic. © 2014 Optical Society of America. Source

Discover hidden collaborations