Architecture and Search Organization for Large Vocabulary Continuous Speech Recognition

This paper gives an overview of an architecture and search organization for large vocabulary, continuous speech recognition (LVCSR at RWTH). In the rst part of the paper, we describe the principle and architecture of a LVCSR system. In particular, the issues of modeling and search for phoneme based recognition are discussed. In the second part, we review the word conditioned lexical tree search algorithm from the viewpoint of how the search space is organized. Further, we extend this method to produce high quality word graphs. Finally, we present some recognition results on the ARPA North American Business (NAB'94) task for a 64000-word vocabulary (American English, continuous speech, speaker independent).

• Type: Conference
• Year: 1997
• Where: GI
• Authors: Stefan Ortmanns, Lutz Welling, Klaus Beulen, Frank Wessel, Hermann Ney
• Keywords: Continuous Speech, Continuous Speech Recognition, GI 1997, Phoneme Based Recognition, Theoretical Computer Science