The RWTH English lecture recognition system

In this paper, we describe the RWTH speech recognition system for English lectures developed within the Translectures project. A difficulty in the development of an English lectures recognition system, is the high ratio of non-native speakers. We address this problem by using very effective deep bot...

Full description

Saved in:
Bibliographic Details
Main Authors: Wiesler, Simon, Irie, Kazuki, Tuske, Zoltan, Schluter, Ralf, Ney, Hermann
Format: Conference Proceeding
Language:English
Subjects:
Acoustics
Adaptation models
Feature extraction
Hidden Markov models
lecture recognition
LVCSR
Speech
speech recognition system
Training
Training data
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we describe the RWTH speech recognition system for English lectures developed within the Translectures project. A difficulty in the development of an English lectures recognition system, is the high ratio of non-native speakers. We address this problem by using very effective deep bottleneck features trained on multilingual data. The acoustic model is trained on large amounts of data from different domains and with different dialects. Large improvements are obtained from unsupervised acoustic adaptation. Another challenge is the frequent use of technical terms and the wide range of topics. In our recognition system, slides, which are attached to most lectures, are used for improving lexical coverage and language model adaptation.
ISSN:1520-6149
2379-190X
DOI:10.1109/ICASSP.2014.6854208