Efficient rule scoring for improved grapheme-based lexicons. Hartmann, W., Lamel, L., & Gauvain, J. In 2014 22nd European Signal Processing Conference (EUSIPCO), pages 1477-1481, Sep., 2014.
![Efficient rule scoring for improved grapheme-based lexicons [pdf]](https://bibbase.org/img/filetypes/pdf.svg "pdf")
Paper abstract bibtex
Paper abstract bibtex For many languages, an expert-defined phonetic lexicon may not exist. One popular alternative is the use of a grapheme-based lexicon. However, there may be a significant difference between the orthography and the pronunciation of the language. In our previous work, we proposed a statistical machine translation based approach to improving grapheme-based pronunciations. Without knowledge of true target pronunciations, a phrase table was created where each individual rule improved the likelihood of the training data when applied. The approach improved recognition accuracy, but required significant computational cost. In this work, we propose an improvement that increases the speed of the process by more than 80 times without decreasing recognition accuracy.
@InProceedings{6952535,
author = {W. Hartmann and L. Lamel and J. Gauvain},
booktitle = {2014 22nd European Signal Processing Conference (EUSIPCO)},
title = {Efficient rule scoring for improved grapheme-based lexicons},
year = {2014},
pages = {1477-1481},
abstract = {For many languages, an expert-defined phonetic lexicon may not exist. One popular alternative is the use of a grapheme-based lexicon. However, there may be a significant difference between the orthography and the pronunciation of the language. In our previous work, we proposed a statistical machine translation based approach to improving grapheme-based pronunciations. Without knowledge of true target pronunciations, a phrase table was created where each individual rule improved the likelihood of the training data when applied. The approach improved recognition accuracy, but required significant computational cost. In this work, we propose an improvement that increases the speed of the process by more than 80 times without decreasing recognition accuracy.},
keywords = {language translation;speech recognition;statistical analysis;rule scoring;improved grapheme-based lexicons;expert-defined phonetic lexicon;orthography;statistical machine translation based approach;language pronunciation;grapheme based pronunciations;automatic speech recognition;Hidden Markov models;Abstracts;Acoustics;automatic speech recognition;grapheme-based speech recognition;pronunciation learning},
issn = {2076-1465},
month = {Sep.},
url = {https://www.eurasip.org/proceedings/eusipco/eusipco2014/html/papers/1569924673.pdf},
}Downloads: 0
{"_id":"44egMLQcYrW6TmNm6","bibbaseid":"hartmann-lamel-gauvain-efficientrulescoringforimprovedgraphemebasedlexicons-2014","authorIDs":[],"author_short":["Hartmann, W.","Lamel, L.","Gauvain, J."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["W."],"propositions":[],"lastnames":["Hartmann"],"suffixes":[]},{"firstnames":["L."],"propositions":[],"lastnames":["Lamel"],"suffixes":[]},{"firstnames":["J."],"propositions":[],"lastnames":["Gauvain"],"suffixes":[]}],"booktitle":"2014 22nd European Signal Processing Conference (EUSIPCO)","title":"Efficient rule scoring for improved grapheme-based lexicons","year":"2014","pages":"1477-1481","abstract":"For many languages, an expert-defined phonetic lexicon may not exist. One popular alternative is the use of a grapheme-based lexicon. However, there may be a significant difference between the orthography and the pronunciation of the language. In our previous work, we proposed a statistical machine translation based approach to improving grapheme-based pronunciations. Without knowledge of true target pronunciations, a phrase table was created where each individual rule improved the likelihood of the training data when applied. The approach improved recognition accuracy, but required significant computational cost. In this work, we propose an improvement that increases the speed of the process by more than 80 times without decreasing recognition accuracy.","keywords":"language translation;speech recognition;statistical analysis;rule scoring;improved grapheme-based lexicons;expert-defined phonetic lexicon;orthography;statistical machine translation based approach;language pronunciation;grapheme based pronunciations;automatic speech recognition;Hidden Markov models;Abstracts;Acoustics;automatic speech recognition;grapheme-based speech recognition;pronunciation learning","issn":"2076-1465","month":"Sep.","url":"https://www.eurasip.org/proceedings/eusipco/eusipco2014/html/papers/1569924673.pdf","bibtex":"@InProceedings{6952535,\n author = {W. Hartmann and L. Lamel and J. Gauvain},\n booktitle = {2014 22nd European Signal Processing Conference (EUSIPCO)},\n title = {Efficient rule scoring for improved grapheme-based lexicons},\n year = {2014},\n pages = {1477-1481},\n abstract = {For many languages, an expert-defined phonetic lexicon may not exist. One popular alternative is the use of a grapheme-based lexicon. However, there may be a significant difference between the orthography and the pronunciation of the language. In our previous work, we proposed a statistical machine translation based approach to improving grapheme-based pronunciations. Without knowledge of true target pronunciations, a phrase table was created where each individual rule improved the likelihood of the training data when applied. The approach improved recognition accuracy, but required significant computational cost. In this work, we propose an improvement that increases the speed of the process by more than 80 times without decreasing recognition accuracy.},\n keywords = {language translation;speech recognition;statistical analysis;rule scoring;improved grapheme-based lexicons;expert-defined phonetic lexicon;orthography;statistical machine translation based approach;language pronunciation;grapheme based pronunciations;automatic speech recognition;Hidden Markov models;Abstracts;Acoustics;automatic speech recognition;grapheme-based speech recognition;pronunciation learning},\n issn = {2076-1465},\n month = {Sep.},\n url = {https://www.eurasip.org/proceedings/eusipco/eusipco2014/html/papers/1569924673.pdf},\n}\n\n","author_short":["Hartmann, W.","Lamel, L.","Gauvain, J."],"key":"6952535","id":"6952535","bibbaseid":"hartmann-lamel-gauvain-efficientrulescoringforimprovedgraphemebasedlexicons-2014","role":"author","urls":{"Paper":"https://www.eurasip.org/proceedings/eusipco/eusipco2014/html/papers/1569924673.pdf"},"keyword":["language translation;speech recognition;statistical analysis;rule scoring;improved grapheme-based lexicons;expert-defined phonetic lexicon;orthography;statistical machine translation based approach;language pronunciation;grapheme based pronunciations;automatic speech recognition;Hidden Markov models;Abstracts;Acoustics;automatic speech recognition;grapheme-based speech recognition;pronunciation learning"],"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"inproceedings","biburl":"https://raw.githubusercontent.com/Roznn/EUSIPCO/main/eusipco2014url.bib","creationDate":"2021-02-13T17:43:41.694Z","downloads":0,"keywords":["language translation;speech recognition;statistical analysis;rule scoring;improved grapheme-based lexicons;expert-defined phonetic lexicon;orthography;statistical machine translation based approach;language pronunciation;grapheme based pronunciations;automatic speech recognition;hidden markov models;abstracts;acoustics;automatic speech recognition;grapheme-based speech recognition;pronunciation learning"],"search_terms":["efficient","rule","scoring","improved","grapheme","based","lexicons","hartmann","lamel","gauvain"],"title":"Efficient rule scoring for improved grapheme-based lexicons","year":2014,"dataSources":["A2ezyFL6GG6na7bbs","oZFG3eQZPXnykPgnE"]}