ASPECTS OF AUTOMATIC SPEECH RECOGNITION BASED ON CONTEXT FREE GRAMMARS FOR NON-NATIVE SPEAKERS
Alina Bogan-Marta, Nicolae Robu · 2003
With the distribution of speech products all over the world, the portability to new target languages becomes a practical concern (Schultz &Waibel,2001). The performance of automatic speech recognizers has been observed to be dramatically worse for speakers with non-native accents than for native speakers. This poses a problem for many speech recognition systems, which need to handle both native and non-native speech. The problem is further complicated by the large number of non-native accents, which makes modeling separate accents difficult, as well as the small amount of nonnative speech that is often available for training. In this paper we intend to show the results of the investigations over the automatic speech recognition engine of a Comand and Control system which is a lexicon tool application based on the L&H Automatic Speech Recognition Software Development Kit (ASR SDK). The study was done using a non-native English speaker and from this perspective we are coming out with aspects encountered during the recognition procedure, analizing them from both the user and designer point of view. At the end there are outlined conclusions over improving techniques.