1992/01/01 by T. Robinson · 1 citation
Computer Science · Mathematics · #Speech Recognition and Synthesis #Speech and dialogue systems #Speech and Audio Processing #Computer science #Connectionism #Context (archaeology) #Hidden Markov model #Pruning #Speech recognition #Phone #Task (project management) #Artificial intelligence #Context model #Vocabulary #Word (group theory) #Heuristic #Markov model #Natural language processing #Markov chain #Artificial neural network #Machine learning #Mathematics
paper · doi:10.1109/icassp.1992.225833
openalex publication_date 1992/01/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/29
A hybrid system using a connectionist model and a Markov model for the DARPA Resource Management task of large-vocabulary multiple-speaker continuous speech recognition is presented. The connectionist model uses internal feedback for context modeling and provides phone state occupancy probabilities for a simple context independent Markov model. The system has been implemented in real-time on a workstation supported by a DSP board. The use of context-independent phone models leads to the possibility of time-domain pruning and computationally efficient durational modeling, both of which are reported.>