9th Annual Conference of the International Speech Communication Association

Brisbane, Australia
September 22-26, 2008

Improving Speech Systems Built from Very Little Data

John Kominek, Sameer Badaskar, Tanja Schultz, Alan W. Black

Carnegie Mellon University, USA

This paper studies two ways for helping non-specialist users develop speech systems from limited data for new languages. Focused web re-crawling finds additional examples of text matching the domain as specified by the user. This improves the language model and cuts word error rate nearly in half. Iterative voice building with interleaved lexicon construction uses the voice from a previous iteration to help construct an improved voice. 4.5 hours of the user's time reduces transcription error rate from 32% to 4%.

Full Paper

Bibliographic reference.  Kominek, John / Badaskar, Sameer / Schultz, Tanja / Black, Alan W. (2008): "Improving speech systems built from very little data", In INTERSPEECH-2008, 1833-1836.