Title :
An advanced system to generate pronunciations of proper nouns
Author :
Deshmukh, Neeraj ; Ngan, Julie ; Hamaker, Jonathan ; Picone, Joseph
Author_Institution :
Inst. for Signal & Inf. Process., Mississippi State Univ., MS, USA
Abstract :
Accurate recognition of proper nouns is a critical component of automatic speech recognition (ASR). Since there are no obvious letter-to-sound conversion rules that govern the pronunciation of any large set of proper nouns, this is an open-ended problem that evolves constantly under various sociolinguistic influences. A Boltzmann machine neural network is well-suited for the task of generating the most likely pronunciations of a proper noun. This pronunciation output can be used to build better acoustic models for the noun that result in improved recognition performance. We present an advanced version of this N-best pronunciations system; and a multiple pronunciations dictionary of 18000 surnames and 25000 pronunciations used as a training database. The database and software are available in the public domain
Keywords :
Boltzmann machines; acoustic signal processing; learning (artificial intelligence); multilayer perceptrons; speech recognition; Boltzmann machine neural network; N-best pronunciations system; acoustic models; automatic speech recognition; multilayered perceptron; multiple pronunciations dictionary; open-ended problem; pronunciation generation; pronunciation output; proper nouns recognition; public domain software; recognition performance; surnames; training database; Automatic speech recognition; Backpropagation; Computational modeling; Databases; Dictionaries; Information processing; Neural networks; Neurons; Signal processing; Simulated annealing;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1997. ICASSP-97., 1997 IEEE International Conference on
Conference_Location :
Munich
Print_ISBN :
0-8186-7919-0
DOI :
10.1109/ICASSP.1997.596226
