Text to Phoneme Alignment and Mapping for Speech Technology: a Neural Networks Approach

John Bullinaria

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

A common problem in speech technology is the alignment of representations of text and phonemes, and the learning of a mapping between them that generalizes well to unseen inputs. The state-of-the-art technology appears to be symbolic rule-based systems, which is surprising given the number of neural network systems for text to phoneme mapping that have been developed over the years. This paper explores why that may be the case, and demonstrates that it is possible for neural networks to simultaneously perform text to phoneme alignment and mapping with performance levels at least comparable to the best existing systems.
Original languageEnglish
Title of host publicationNeural Networks (IJCNN), The 2011 International Joint Conference on
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages625-632
Number of pages8
ISBN (Print)978-1-4244-9635-8
DOIs
Publication statusPublished - 5 Jul 2011
EventProceedings of the International Joint Conference on Neural Networks (IJCNN 2011) -
Duration: 5 Jul 2011 → …

Conference

ConferenceProceedings of the International Joint Conference on Neural Networks (IJCNN 2011)
Period5/07/11 → …

Fingerprint

Dive into the research topics of 'Text to Phoneme Alignment and Mapping for Speech Technology: a Neural Networks Approach'. Together they form a unique fingerprint.

Cite this