Abstract: "We present a multi-network connectionist architecture that forms distributed low-level knowledge representations critical to robust pattern recognition in non-stationary stochastic processes. This new network comprises a number of stimulus-specific sub-networks (i.e., networks traine...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Hampshire, John B. (VerfasserIn), Waibel, Alex H. (VerfasserIn)
Format:	Buch
Sprache:	English
Veröffentlicht:	Pittsburgh, Pa. 1989
Schriftenreihe:	Carnegie-Mellon University <Pittsburgh, Pa.> / Computer Science Department: CMU-CS 89,166
Schlagworte:	Automatic speech recognition Pattern recognition systems
Zusammenfassung:	Abstract: "We present a multi-network connectionist architecture that forms distributed low-level knowledge representations critical to robust pattern recognition in non-stationary stochastic processes. This new network comprises a number of stimulus-specific sub-networks (i.e., networks trained to classify a particular type of stimulus) that are linked by a combinational superstructure. The combinational superstructure adapts to the stimulus being processed, optimally integrating stimulus-specific classifications based on its internally-developed model of the stimulus or combination of stimuli most likely to have produced the input signal. To train this combinational network we have developed a new form of multiplicative connection that we call the "Meta-Pi" connection. We illustrate how the Meta-Pi paradigm implements a dynamically adaptive Bayesian connectionist classifier We demonstrate the Meta-Pi architecture's performance in the context of multi-speaker phoneme recognition. In this task the Meta-Pi superstructure integrates conflict-arbitrated Time-Delay Neural Network (TDNN) sub-networks to perform multi-speaker phoneme recognition at speaker-dependent rates. It achieves a 6-speaker (4 males, 2 females) recognition rate of 98.4% on a database of voiced-stops (/b,d,g/). This recognition performance constitutes a significant improvement over the 95.9% multi-speaker recognition rate obtained by a single TDNN trained in multi-speaker fashion. It also approaches the 98.7% average of the speaker-dependent recognition rates for the six speakers processed. We show that the Meta-Pi network can learn--without direct supervision--to recognize the speech of one particular speaker using a dynamic combination of internal models of other speakers exclusively (99.8% correct). The Meta-Pi model constitutes a viable basis for connectionist pattern recognition systems that can rapidly adapt to new stimuli by using dynamic, conditional combinations of existing stimulus-specific models.
Beschreibung:	32 S.