000192654 001__ 192654
000192654 005__ 20190316235804.0
000192654 037__ $$aREP_WORK
000192654 088__ $$aIdiap-RR-10-2013
000192654 245__ $$aAdaptation Experiments on French MediaParl ASR
000192654 269__ $$a2013
000192654 260__ $$bIdiap$$c2013
000192654 336__ $$aReports
000192654 520__ $$aThis document summarizes adaptation experiments done on French MediaParl corpus and other French corpora. Baseline adaptation techniques are briefly presented and evaluated in the MediaParl task for speaker adaptation, speaker adaptive training, database combination and environmental adaptation. Results show that by applying baseline adaptation techniques, a relative WER reduction of up to 22.8% can be reached in French transcription accuracy. For the MediaParl task, performance of systems trained on directly merged databases and of systems trained on databases combined via MAP adaptation did not differ significantly when large amount of data was available. During the experiments, French data recorded in Switzerland behaved in a similar way compared to French data recorded in France, which suggest that French spoken in Valais is close to the standard French spoken in France, and differencies in ASR accuracies between models trained on Swiss MediaParl and on French BREF are more likely caused by environmental factors or more spontaneity in speech.
000192654 700__ $$aSzaszak, Gyorgy
000192654 8564_ $$uhttps://infoscience.epfl.ch/record/192654/files/Szaszak_Idiap-RR-10-2013.pdf$$zn/a$$s499543$$yn/a
000192654 909C0 $$xU10381$$0252189$$pLIDIAP
000192654 909CO $$ooai:infoscience.tind.io:192654$$qGLOBAL_SET$$pSTI$$preport
000192654 937__ $$aEPFL-REPORT-192654
000192654 970__ $$aSzaszak_Idiap-RR-10-2013/LIDIAP
000192654 973__ $$aEPFL
000192654 980__ $$aREPORT