Probabilistic analysis of pronunciation with 'MAUS'

Abstract

This paper describes a method to automatically detect pronunciation variants in large speech corpora within the framework of the 'MAUS' project. 'MAUS' stands for 'Munich Automatic Segmentation System' and is a general purpose tool to automatically label and segment read and spontaneous German speech into phonetic/phonologic segments. The output of MAUS can for example be used to build probabilistic models of pronunciation of fluent German as reflected by the analysed corpus. These models can be the basis for phonetic investigations or can be incorporated into classic speech recognition algorithms.