This paper introduces a class of statistical mechanisms, called hidden understanding models, for natural language processing. Much of the framework for hidden understanding models...
Scott Miller, Richard M. Schwartz, Robert J. Bobro...
In this paper we describe a method for Minimum Bayes Risk decoding for speech recognition. This is a technique similar to Consensus a.k.a. Confusion Network Decoding, in which we ...
The Hidden Markov Model (HMM) has been widely used in many applications such as speech recognition. A common challenge for applying the classical HMM is to determine the structure...
Today, a large number of audio features exists in audio retrieval for different purposes, such as automatic speech recognition, music information retrieval, audio segmentation, an...
Dalibor Mitrovic, Matthias Zeppelzauer, Christian ...
In this paper, we propose a PLSA-based language model for sports live speech. This model is implemented in unigram rescaling technique that combines a topic model and an n-gram. I...