Show simple item record

Neural Networks That Recognize Phonemes by Their Acoustic Features

dc.contributor.advisorShamma, S.A.en_US
dc.contributor.authorWang, K.en_US
dc.description.abstractThe ability of the ear model and lateral inhibitory networks (LIN) to preserve and enhance acoustic features of speech signal is examined by training neural networks to recognize phonemes by their LIN outputs. Using the back propagation learning algorithm, networks that are specialized to recognize specific classes of phonemes are trained and tested. Experiments are conducted both in single and multi-speaker cases. By using single layer networks, we can show that the phonemes are identified by their acoustic features that have been known to linguists and phoneticians. The networks generally yield satisfying results when tested in experiments for a single speaker, where we focus on the performance against phoneme variation induced by the context, and in multi-speaker experiments where errors in recognition are due to speaker variation. These results convince us that the acoustic features picked by the networks are reliable cues for phoneme recognitionen_US
dc.format.extent2964016 bytes
dc.relation.ispartofseriesISR; MS 1991-1en_US
dc.subjectneural systemsen_US
dc.subjectsignal processingen_US
dc.subjectspeech processingen_US
dc.subjectauditory modelen_US
dc.subjectCommunication en_US
dc.subjectSignal Processing Systemsen_US
dc.titleNeural Networks That Recognize Phonemes by Their Acoustic Featuresen_US

Files in this item


This item appears in the following Collection(s)

Show simple item record