Large vocabulary continuous speech recognition of Broadcast News - The Philips/RWTH approach

Automatic speech recognition of real-live broadcast news (BN) data (Hub-4) has become a challenging research topic in recent years. This paper summarizes our key efforts to build a large vocabulary continuous speech recognition system for the heterogenous BN task without inducing undesired complexity and computational resources. These key efforts included:

• Type: Journal
• Year: 2002
• Where: SPEECH
• Authors: Peter Beyerlein, Xavier L. Aubert, Reinhold Haeb-Umbach, Matthew Harris, Dietrich Klakow, Andreas Wendemuth, Sirko Molau, Hermann Ney, Michael Pitz, Achim Sixtus
• Keywords: Key Efforts, SPEECH 2002, Speech Recognition, Word Error Rate