000213707 001__ 213707
000213707 005__ 20180317093314.0
000213707 037__ $$aREP_WORK
000213707 088__ $$aIdiap-RR-32-2015
000213707 245__ $$aHMM-based Non-native Accent Assessment using Posterior Features
000213707 269__ $$a2015
000213707 260__ $$bIdiap$$c2015
000213707 336__ $$aReports
000213707 520__ $$aAutomatic non-native accent assessment has many potential benefits in language learning and speech technologies. The three fundamental challenges in automatic accent assessment are to characterize, model and assess individual variation in speech of the non-native speaker. In our recent work, accentedness score was automatically obtained by comparing two phone probability sequences obtained through instances of non-native and native speech. In this paper, we build on the previous work and obtain the native latent symbol probability sequence through the word hypothesis modeled as a hidden Markov model (HMM). The approach overcomes the necessity for a native human reference speech of the same sentence. Using the HMMs trained on an auxiliary native speech corpus, the proposed approach achieves a correlation of 0.68 with the human accent ratings on the ISLE corpus. This is further interesting considering that the approach does not use any non-native data and human accent ratings at any stage of the  system development.
000213707 6531_ $$aAutomatic accent assessment
000213707 6531_ $$aKL-divergence
000213707 6531_ $$aKL-HMM
000213707 6531_ $$alexical model
000213707 6531_ $$anon-native speech
000213707 6531_ $$aPosterior features
000213707 700__ $$0246039$$aRasipuram, Ramya$$g197868
000213707 700__ $$aCernak, Milos
000213707 700__ $$0243959$$aMagimai.-Doss, Mathew$$g127186
000213707 8564_ $$s576023$$uhttps://infoscience.epfl.ch/record/213707/files/Rasipuram_Idiap-RR-32-2015.pdf$$yn/a$$zn/a
000213707 909CO $$ooai:infoscience.tind.io:213707$$preport$$pSTI
000213707 909C0 $$0252189$$pLIDIAP$$xU10381
000213707 937__ $$aEPFL-REPORT-213707
000213707 970__ $$aRasipuram_Idiap-RR-32-2015/LIDIAP
000213707 980__ $$aREPORT