Minimum error rate training (MERT) involves choosing parameter values for a machine translation (MT) system that maximize performance on a tuning set as measured by an automatic e...
This paper presents a novel formulation and approach to the minimal document set retrieval problem. Minimal Document Set Retrieval (MDSR) is a promising information retrieval task...
The recently developed i-vector framework for speaker recognition has set a new performance standard in the research field. An i-vector is a compact representation of a speaker u...
—The call-level performance modelling and evaluation of 3G cellular networks is important for the proper network dimensioning and efficient use of the network resources, such as ...
This paper presents the development and evaluation of a speaker-independent audio-visual speech recognition (AVSR) system that utilizes a segment-based modeling strategy. To suppo...
Timothy J. Hazen, Kate Saenko, Chia-Hao La, James ...