J. Org Rottl

Tied-Posteriors: A New Hybrid Speech Recognition Technology with Generic Capabilities and High Portability (2007)

Jan Stadermann, Jörg Rottland, J Org Rottl, Gerhard Rigoll

This paper presents a new method for estimating the emission probabilities of general hybrid connectionist/HMM recognition systems. Contrary to the traditional hybrid approach, where a neural network...

Efficient Computation Of MMI Neural Networks For Large Vocabulary Speech Recognition Systems (2007)

Jörg Rottland, J Org Rottl, André Lüdecke, Gerhard Rigoll

This paper describes, how to train Maximum Mutual Information Neural Networks (MMINN) in an efficient way, with a new topology. Large vocabulary speech recognition systems, based on a Hybrid...

TIED POSTERIORS: AN APPROACH FOR EFFECTIVE INTRODUCTION OF CONTEXT DEPENDENCY IN HYBRID NN/HMM LVCSR (2007)

J Org Rottl, Gerhard Rigoll

Speaker Adaptation Using Regularization And Network Adaptation For Hybrid MMI-NN/HMM Speech Recognition (1999)

Jörg Rottland, J Org Rottl, Christoph Neukirchen, Daniel Willett, Gerhard Rigoll

This paper describes, how to perform speaker adaptation for a hybrid large vocabulary speech recognition system. The hybrid system is based on a Maximum Mutual Information Neural Network (MMINN),...

Refining Tree-Based State Clustering by Means of Formal Concept Analysis, Balanced Decision Trees and Automatically Generated Model-Sets (1999)

Daniel Willett, Christoph Neukirchen, Jörg Rottland, J Org Rottl, Gerhard Rigoll

Decision tree-based state clustering has emerged in recent years as the most popular approach for clustering the states of context dependent hidden Markov model based speech recognizers. The...