Learn More
MPE (Minimum Phone Error) is a previously introduced technique for discriminative training of HMM parameters. fMPE applies the same objective function to the features, transforming the data with a kernel-like method and training millions of parameters, comparable to the size of the acoustic model. Despite the large number of parameters, fMPE is robust to(More)
In recent work, we proposed the rational all-pass transform (RAPT) as the basis of a speaker adaptation scheme intended for use with a large vocabulary speech recognition system. It was shown that RAPT-based adaptation reduces to a linear transformation of cepstral means, much like the better known maximum likelihood linear regression (MLLR). In a set of(More)
Deep Convolutional Neural Networks (CNNs) are more powerful than Deep Neural Networks (DNN), as they are able to better reduce spectral variation in the input signal. This has also been confirmed experimentally, with CNNs showing improvements in word error rate (WER) between 4-12% relative compared to DNNs across a variety of LVCSR tasks. In this paper, we(More)
Oral communication is transient but many important decisions, social contracts and fact 'ndings are 'rst canied out in an oral setup, documented in written form and later retrieved. At Carnegie Mel-lons University s Interactive Systems Laboratories we have been experimenting with the documentation of meetings. T h s paper summarizes part of the progress(More)
Since we cannot exclude that speech recognizers fail sometimes , it is important to examine how users react to recognition errors. In correction situations, speaking style becomes more accentuated to disambiguate the original mistake. We examine the effect of speaking style in such situations on speech recognition performance. Our results indicate that(More)