The authors explore pattern recognition techniques for verifying the correctness of a pronunciation lexicon, focusing on techniques that require limited human interaction. They evaluate the British English Example Pronunciation (BEEP) dictionary [1], a popular public domain resource that is widely used in English speech processing systems. The techniques being investigated are applied to the lexicon and the results of each step are illustrated using sample entries. The authors found that as many as 5553 words in the BEEP dictionary are incorrect. They demonstrate the effect of correction techniques on a lexicon and implement the lexicon in an automatic speech recognition (ASR) system
Reference:
Martirosian, O and Davel, M. 2007. Error analysis of a public domain pronunciation dictionary. 18th Annual Symposium of the Pattern Recognition Association of South Africa (PRASA 2007), Pietermaritzburg, Kwazulu-Natal, South Africa, 28-30 November 2007, pp 13
Martirosian, O., & Davel, M. (2007). Error analysis of a public domain pronunciation dictionary. 18th Annual Symposium of the Pattern Recognition Association of South Africa (PRASA 2007). http://hdl.handle.net/10204/1973
Martirosian, O, and M Davel. "Error analysis of a public domain pronunciation dictionary." (2007): http://hdl.handle.net/10204/1973
Martirosian O, Davel M, Error analysis of a public domain pronunciation dictionary; 18th Annual Symposium of the Pattern Recognition Association of South Africa (PRASA 2007); 2007. http://hdl.handle.net/10204/1973 .
