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

13 years 4 months ago

Download www-i6.informatik.rwth-aachen.de

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:

Peter Beyerlein, Xavier L. Aubert, Reinhold Haeb-U

Real-time Traffic

Key Efforts | SPEECH 2002 | Speech Recognition | Word Error Rate |

claim paper

» First Broadcast News Transcription System for Khmer Language

» Language Identification via Large Vocabulary Speaker Independent Continuous Speech Recogni...

» Processing Broadcast Audio for Information Access

» Combining Spectral Representations for LargeVocabulary Continuous Speech Recognition

» Learning SubWord Units for Open Vocabulary Speech Recognition

» Phonetic pronunciations for arabic speechtotext systems

» LargeMargin Discriminative Training of Hidden Markov Models for Speech Recognition

» Morphologybased and subword language modeling for Turkish speech recognition

Post Info
More Details (n/a)

Added	23 Dec 2010
Updated	23 Dec 2010
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

Comments (0)

Sciweavers

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

Key Efforts | SPEECH 2002 | Speech Recognition | Word Error Rate |

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers