Multiple models for improved speech recognition for non-native speakers
暂无分享,去创建一个
Speech recognition of foreign accented speech is one of the most difficult tasks in ASR. The problem of foreign accent is addressed in this study using acoustic models of the target language phonemes (French phonemes in our case) adapted with speech data from 3 other languages: English (US and UK), German and Spanish. Recognition results obtained for 11 language groups of speakers show that error rate can be significantly reduced when standard acoustic models of phonemes are adapted using speech data from other languages. Phonological rules are also introduced into the standard phonetic description of the lexical units to account for some foreign accent pronunciation variants. It appears that using phonological rules together with foreign language adapted acoustic units provides the best recognition performance. The highest error rate reduction (40%) is obtained on English speakers.
[1] James Emil Flege,et al. Interaction between the native and second language phonetic subsystems , 2003, Speech Commun..
[2] Ralf Kompe,et al. Generating non-native pronunciation variants for lexicon adaptation , 2004, Speech Commun..
[3] Katarina Bartkova,et al. Language based phone model combination for ASR adaptation to foreign accent , 1999 .