Start ReadSpeaker XT

Contact




Seminar at Speech, Music and Hearing:

Assessing and Improving the Performance of Speech Recognition for Incremental Systems

OBS! In the seminar room

Timo Baumann - Doctoral guest researcher, Potsdam University

Abstract

In incremental spoken dialogue systems, partial hypotheses about what was said are required even while the utterance is still ongoing. We define measures for evaluating the quality of incremental ASR components with respect to the _relative correctness_ of the partial hypotheses compared to hypotheses that can optimize over the complete input, the _timing_ of hypothesis formation relative to the portion of the input they are about, and hypothesis _stability_, defined as the number of times they are revised. We show that simple incremental post-processing can improve stability dramatically, at the cost of timeliness (from 90 % of edits of hypotheses being spurious down to 10 % at a lag of 320 ms). The measures are not independent, and we show how system designers can find a desired operating point for their ASR. To our knowledge, we are the first to suggest and examine a variety of measures for assessing incremental ASR and improve performance on this basis.

15:15 - 17:00
Friday May 29, 2009

The seminar is held in Seminar room.

| Show complete seminar list







Published by: TMH, Speech, Music and Hearing
Webmaster, webmaster@speech.kth.se

Last updated: Wednesday, 23-Jun-2010 09:22:46 MEST