In this work, investigations in the course of the developement of RWTH automatic speech recognition systems developed for the second TC-STAR evaluation campaign 2006 are presented. The systems were designed to transcribe parliamentary speeches taken from the European Parliament Plenary Sessions (EPPS) in European English and Spanish, as well as speeches from the Spanish Parliament. The RWTH sys...

In the past few years, deep neural networks (DNNs) have achieved great successes in speech recognition. The deep network model can be viewed as a series of feature transforms followed by a log-linear classifier. For input of speeches from different bandwidths, although the hidden layer transform and log-linear classification can be shared, the input layer transforms should be specially designed...

This paper addresses the problem of automatic recognition of three simultaneous speeches with two microphones, that is, that of sound source separation where the number of sound sources is greater than that of microphones. The approach used is the direction-pass filter, which is implemented by hypothetical reasoning on the interaural phase difference (IPD) and interaural intensity difference (I...

UNL-ization is the process of converting Natural Language resource to Universal Natural Language (i.e., UNL). UNL is based on Interlingua approach, specifically designed by UNDL foundation for storing, summarizing, representing and describing information in a format which is independent to a natural language. This paper illustrates UNL-ization of Punjabi language with the help of IAN (i.e., Int...

Certain irregularities in utterances of a word or phrase occur in English as spoken by Japanese native subjects (Japanese English, henceforth). This study considers such pitch patterns as one of the most common causes of deficiencies in Japanese English, and that Japanese English would have better pitch patterns if its peculiarities are modified. Firstly, pitch patterns of Japanese English are ...