Return to search

Channel Modeling Applied to Robust Automatic Speech Recognition

In automatic speech recognition systems (ASRs), training is a critical phase to the system?s success. Communication media, either analog (such as analog landline phones) or digital (VoIP) distort the speaker?s speech signal often in very complex ways: linear distortion occurs in all channels, either in the magnitude or phase spectrum. Non-linear but time-invariant distortion will always appear in all real systems. In digital systems we also have network effects which will produce packet losses and delays and repeated packets. Finally, one cannot really assert what path a signal will take, and so having error or distortion in between is almost a certainty. The channel introduces an acoustical mismatch between the speaker's signal and the trained data in the ASR, which results in poor recognition performance. The approach so far, has been to try to undo the havoc produced by the channels, i.e. compensate for the channel's behavior. In this thesis, we try to characterize the effects of different transmission media and use that as an inexpensive and repeatable way to train ASR systems.

Identiferoai:union.ndltd.org:UMIAMI/oai:scholarlyrepository.miami.edu:oa_theses-1086
Date01 January 2007
CreatorsSklar, Alexander Gabriel
PublisherScholarly Repository
Source SetsUniversity of Miami
Detected LanguageEnglish
Typetext
Formatapplication/pdf
SourceOpen Access Theses

Page generated in 0.0024 seconds