The RWTH large vocabulary continuous speech recognition system
Hermann NeyL. WellingS. OrtmannsK. BeulenFrank Wessel
Abstract
We present an overview of the RWTH Aachen large vocabulary continuous speech recognizer. The recognizer is based on continuous density hidden Markov models and a time-synchronous left-to-right beam search strategy. Experimental results on the ARPA Wall Street Journal (WSJ) corpus verify the effects of several system components, namely linear discriminant analysis, vocal tract normalization, pronunciation lexicon and cross-word triphones, on the recognition performance.
Metrics
Citation History
Topics
Related Documents
Large vocabulary continuous speech recognition of Broadcast News – The Philips/RWTH approach
Peter BeyerleinXavier AubertReinhold Haeb‐UmbachMatthew HarrisDietrich KlakowAndreas WendemuthSirko MolauHermann NeyMichael PitzAchim Sixtus
Recent improvements of the RWTH large vocabulary speech recognition system on spontaneous speech
Achim SixtusSirko MolauStephan KanthakRalf SchlüterHermann Ney
Large Vocabulary Continuous Speech Recognition System for Marathi
Snehal Chandulal BajajKamal KantAmol BolePranaw Kumar
A Myanmar large vocabulary continuous speech recognition system
Hay Mar Soe NaingAye Mya HlaingWin Pa PaXinhui HuYe Kyaw ThuChiori HoriHisashi Kawai
The RWTH Large Vocabulary Arabic Handwriting Recognition System
Mahdi HamdaniPatrick DoetschMichał KozielskiAmr El-Desoky MousaHermann Ney