Learn More
A new database project has been launched in Estonia last year. It aims the collection of telephone speech from a large number of speakers for speech and speaker recognition purposes. Up to 2000 speakers are expected to participate in recordings. SpeechDat databases, especially Finnish SpeechDat, have been chosen as a prototype for the Estonian database. It(More)
This paper deals with the perceptual assessment of Russian-accented Estonian. Speech samples were recorded from 20 speakers with a Russian background; clips of about 20 seconds from each speaker were selected for this perceptual study. The accentedness was rated in two tests: first, 20 native Estonian speakers judged the samples and rated the degree of(More)
The paper studies the production and perception of Estonian quantity oppositions by native Estonians (L1 subjects) and non-native speakers with Russian-language background (L2 subjects). Estonian quantity system involves three contrastive prosodic patterns referred to as short (Q1), long (Q2) and overlong (Q3) quantity degrees. These phonological contrasts(More)