Meinhard Ullrich

Learn More
The performance of the Philips system for large vocabulary continuous speech recognition has been improved signi cantly by crossword N-phone modelling, enhanced clustering of HMM-states during training, consistent handling of untrained HMM-states during decoding and a new e cient crossword N-phone M-gram decoding strategy. We report word error rate(More)
In this paper we describe some characteristics of the acoustic modeling used in the Philips continuous-speech recognition system for the DARPA Hub-4 1997 evaluation, which are related to robustness issues. We aimed at a conceptually simple system: We trained two model sets on 70 hours of the Hub4 training data, one for within-word and one for cross-word(More)
In this paper the Philips Broadcast News transcription system is described. The Broadcast News task aims at the recognition of \found" speech in radio and television broadcasts without any additional side information (e.g. speaking style, background conditions). The system was derived from the Philips continuous mixture density crossword HMM system, using(More)
This paper presents an extension of bottom-up state-tying towards improved handling of unseen triphones. As opposed to the usual backing-o to diphones and monophones, the current method aims at nding a triphone model that has proven to exhibit some similarity with the unseen triphone. It is based on a probabilistic mapping of unseen contexts to clusters of(More)
  • 1