Which ASR should I choose for my dialogue system
Fabrizio Morbini, Kartik Audhkhasi, Kenji Sagae, Ron Artstein, Doğan Can, Panayiotis Georgiou, S. R. Narayanan, Anton Leuski, David R. Traum · 2013
We present an analysis of several pub-licly available automatic speech recogniz-ers (ASRs) in terms of their suitability for use in different types of dialogue systems. We focus in particular on cloud based ASRs that recently have become available to the community. We include features of ASR systems and desiderata and re-quirements for different dialogue systems, taking into account the dialogue genre, type of user, and other features. We then present speech recognition results for six different dialogue systems. The most in-teresting result is that different ASR sys-tems perform best on the data sets. We also show that there is an improvement over a previous generation of recognizers on some of these data sets. We also inves-tigate language understanding (NLU) on the ASR output, and explore the relation-ship between ASR and NLU performance. 1