EURASIP Journal on Audio, Speech, and Music Processing

Table 3 Comparison of acoustic models with different balance of Czech and Spanish training data evaluated over typical Spanish voices

From: A cross-lingual adaptation approach for rapid development of speech recognizers for learning disabled users

Acoustic model	ACC (%)	DR (%)	FA [1/kw/h]
AM_cz&ES_cross	54.10	85.88	1.94
AM_CZ&es	52.30	81.42	2.03
AM_CZ	45.75	57.00	0.46

Back to article page