Cross-language bootstrapping based on completely unsupervised training using multilingual A-stabil

Abstract

This paper presents our work on rapid language adaptation of acoustic models based on multilingual cross-language bootstrapping and unsupervised training. We used Automatic Speech Recognition (ASR) systems in English, French, German, and Spanish to build a Czech ASR system from scratch. System building was performed without using any transcribed audio data… (More)
DOI: 10.1109/ICASSP.2011.5947479

8 Figures and Tables

Topics

Statistics

051015201520162017
Citations per Year

Citation Velocity: 7

Averaging 7 citations per year over the last 3 years.

Learn more about how we calculate this metric in our FAQ.
  • Presentations referencing similar topics