Word recognition using hidden Markov models and neural associative memories
Kara Kayikci, Zöhre
FacultiesFakultät für Ingenieurwissenschaften und Informatik
LicenseStandard (Fassung vom 01.10.2008)
In this thesis a novel hybrid approach to automatic speech recognition (ASR) has been proposed. This hybrid system is based on hidden Markov models (HMMs) on the subword-unit level and neural associative memories (NAMs) on the word and language levels. The focus of the work is to develop a flexible and robust speech recognition system against real-world environments and to augment the recognition performance. The developed hybrid system consists of two parts: HMM-based subword-unit recognition and NAM based word recognition, which is also composed of single word recognition network and language model network. The developed hybrid system is also a part of a language processing system embedded in a mobil robot. For a given speech utterance the developed hybrid system recognizes words and forwards them to the NAM based sentence understanding module in the language processing system. Within the scope of this thesis different features of the developed hybrid system were investigated. These features include representation and handling of ambiguities on different levels and incremental extension of task vocabulary with novel words. The proposed hybrid speech recognition system has been successfully applied to various recognition tasks. Compared to other HMM-based speech recognition systems in the literature, competitive recognition results were achieved.
Subject HeadingsWorterkennung [GND]
Hidden Markov models [LCSH]
Word recognition [LCSH]