Application of a fast real time recurrent learning algorithm to text-to-phoneme conversion

Yee Ling Lu; Man Wai Mak; Wan Chi Siu

Application of a fast real time recurrent learning algorithm to text-to-phoneme conversion

Yee Ling Lu, Man Wai Mak, Wan Chi Siu

The Hong Kong Polytechnic University

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

6 Citations (Scopus)

Abstract

This paper attempts to perform text-to-phoneme conversion by using recurrent neural networks trained with the real time recurrent learning (RTRL) algorithm. As recurrent neural networks deal well with spatial temporal problems, they are proposed to tackle the problem of converting English text streams into their corresponding phonetic transcriptions. We found that, due to the high computational complexity, the original RTRL algorithm takes a long time to finish the learning. We propose a fast RTRL algorithm (FRTRL), with a lower computational complexity, to shorten the time consumed in the learning process.

Original language	English
Title of host publication	IEEE International Conference on Neural Networks - Conference Proceedings
Publisher	IEEE
Pages	2853-2857
Number of pages	5
Publication status	Published - 1 Dec 1995
Event	Proceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6) - Perth, Australia Duration: 27 Nov 1995 → 1 Dec 1995

Conference

Conference	Proceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6)
Country/Territory	Australia
City	Perth
Period	27/11/95 → 1/12/95

ASJC Scopus subject areas

Software

Cite this

@inproceedings{d28830afb78d48b693124646d1eade84,

title = "Application of a fast real time recurrent learning algorithm to text-to-phoneme conversion",

abstract = "This paper attempts to perform text-to-phoneme conversion by using recurrent neural networks trained with the real time recurrent learning (RTRL) algorithm. As recurrent neural networks deal well with spatial temporal problems, they are proposed to tackle the problem of converting English text streams into their corresponding phonetic transcriptions. We found that, due to the high computational complexity, the original RTRL algorithm takes a long time to finish the learning. We propose a fast RTRL algorithm (FRTRL), with a lower computational complexity, to shorten the time consumed in the learning process.",

author = "Lu, {Yee Ling} and Mak, {Man Wai} and Siu, {Wan Chi}",

year = "1995",

month = dec,

day = "1",

language = "English",

pages = "2853--2857",

booktitle = "IEEE International Conference on Neural Networks - Conference Proceedings",

publisher = "IEEE",

address = "United States",

note = "Proceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6) ; Conference date: 27-11-1995 Through 01-12-1995",

}

Application of a fast real time recurrent learning algorithm to text-to-phoneme conversion. / Lu, Yee Ling; Mak, Man Wai; Siu, Wan Chi.
IEEE International Conference on Neural Networks - Conference Proceedings. IEEE, 1995. p. 2853-2857.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - Application of a fast real time recurrent learning algorithm to text-to-phoneme conversion

AU - Lu, Yee Ling

AU - Mak, Man Wai

AU - Siu, Wan Chi

PY - 1995/12/1

Y1 - 1995/12/1

N2 - This paper attempts to perform text-to-phoneme conversion by using recurrent neural networks trained with the real time recurrent learning (RTRL) algorithm. As recurrent neural networks deal well with spatial temporal problems, they are proposed to tackle the problem of converting English text streams into their corresponding phonetic transcriptions. We found that, due to the high computational complexity, the original RTRL algorithm takes a long time to finish the learning. We propose a fast RTRL algorithm (FRTRL), with a lower computational complexity, to shorten the time consumed in the learning process.

AB - This paper attempts to perform text-to-phoneme conversion by using recurrent neural networks trained with the real time recurrent learning (RTRL) algorithm. As recurrent neural networks deal well with spatial temporal problems, they are proposed to tackle the problem of converting English text streams into their corresponding phonetic transcriptions. We found that, due to the high computational complexity, the original RTRL algorithm takes a long time to finish the learning. We propose a fast RTRL algorithm (FRTRL), with a lower computational complexity, to shorten the time consumed in the learning process.

UR - http://www.scopus.com/inward/record.url?scp=0029457586&partnerID=8YFLogxK

M3 - Conference article published in proceeding or book

SP - 2853

EP - 2857

BT - IEEE International Conference on Neural Networks - Conference Proceedings

PB - IEEE

T2 - Proceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6)

Y2 - 27 November 1995 through 1 December 1995

ER -

Application of a fast real time recurrent learning algorithm to text-to-phoneme conversion

Abstract

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this