Information fusion approaches to the automatic pronunciation of print by analogy

Damper, R. I.; Marchand, Yannick

doi:10.1016/j.inffus.2004.08.002

Cited by 13 publications

(10 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When an unknown word is presented as an input to the system, so-called full pattern matching between the input letter string and database In our previous syllabification work using analogy (Marchand & Damper, 2007), we obtained best results by combining only 3 of the 5 scoring strategies when choosing between tied shortest paths. These were the product of arc frequencies, the frequency of the same pronunciation, and the 'weak link' (see Marchand &Damper, 2000 andDamper &Marchand, 2006 for full specification). Accordingly, in this work, these same three scoring strategies are used exclusively, and combined by rank fusion 7 , for SbA.…”

Section: Data-driven Methodsmentioning

confidence: 99%

Automatic Syllabification in English: A Comparison of Different Algorithms

2009

View full text Add to dashboard Cite

Automatic syllabification of words is challenging, not least because the syllable is not easy to define precisely. Consequently, no accepted standard algorithm for automatic syllabification exists. There are two broad approaches: rule-based and data-driven. The rule-based method effectively embodies some theoretical position regarding the syllable, whereas the data-driven paradigm tries to infer “new” syllabifications from examples assumed to be correctly syllabified already. This article compares the performance of several variants of the two basic approaches. Given the problems of definition, it is difficult to determine a correct syllabification in all cases and so to establish the quality of the “gold standard” corpus used either to evaluate quantitatively the output of an automatic algorithm or as the example-set on which data-driven methods crucially depend. Thus, we look for consensus in the entries in multiple lexical databases of pre-syllabified words. In this work, we have used two independent lexicons, and extracted from them the same 18,016 words with their corresponding (possibly different) syllabifications. We have also created a third lexicon corresponding to the 13,594 words that share the same syllabifications in these two sources. As well as two rule-based approaches (Hammond's and Fisher's implementation of Kahn's), three data-driven techniques are evaluated: a look-up procedure, an exemplar-based generalization technique, and syllabification by analogy (SbA). The results on the three databases show consistent and robust patterns. First, the data-driven techniques outperform the rule-based systems in word and juncture accuracies by a very significant margin but require training data and are slower. Second, syllabification in the pronunciation domain is easier than in the spelling domain. Finally, best results are consistently obtained with SbA.

show abstract

Section: Data-driven Methodsmentioning

confidence: 99%

Automatic Syllabification in English: A Comparison of Different Algorithms

2009

View full text Add to dashboard Cite

show abstract

“…The current state of the art in pronunciation by analogy is well summarized by the following passage from Damper and Marchand (2006):…”

Section: Resultsmentioning

confidence: 99%

A probabilistic approach to pronunciation by analogy

Kujala¹

2013

Computer Speech & Language

View full text Add to dashboard Cite

The relationship between written and spoken words is convoluted in languages with a deep orthography such as English and therefore it is difficult to devise explicit rules for generating the pronunciations for unseen words. Pronunciation by analogy (PbA) is a data-driven method of constructing pronunciations for novel words from concatenated segments of known words and their pronunciations. PbA performs relatively well with English and outperforms several other proposed methods. However, the best published word accuracy of 65.5% (for the 20,000 word NETtalk corpus) suggests there is much room for improvement in it.Previous PbA algorithms have used several different scoring strategies such as the product of the frequencies of the component pronunciations of the segments, or the number of different segmentations that yield the same pronunciation, and different combinations of these methods, to evaluate the candidate pronunciations. In this article, we instead propose to use a probabilistically justified scoring rule. We show that this principled approach alone yields better accuracy (66.21% for the NETtalk corpus) than any previously published PbA algorithm. Furthermore, combined with certain ad hoc modifications motivated by earlier algorithms, the performance climbs up to 66.6%, and further improvements are possible by combining this method with other methods.

show abstract

“…In recent work, Damper and Marchand (2006) showed that this rank fusion approach gives statistically significant performance improvements over simpler versions of PbA and over the several other fusion schemes that were tried. Individual points are then multiplied together to produce a final overall score and the best-scoring pronunciation is selected.…”

Section: Principles Of Pronunciation By Analogymentioning

confidence: 96%

“…Pronunciation by analogy is a data-driven technique for converting spelling to sound that is attracting increasing attention as an automatic pronunciation method for text-to-speech (TTS) synthesis (e.g., Dedina and Nusbaum, 1991; Sullivan and Damper, 1993; Federici, Pirrelli and Yvon, 1995; Damper and Eastmond, 1997; Yvon 1996a, b; Bagshaw 1998; Marchand and Damper, 2000; Sullivan, 2001; Damper and Marchand, 2006). This has been driven by accumulating evidence that PbA easily outperforms traditional linguistic rewrite rules as used extensively in earlier TTS systems plus a variety of other data-driven methods for spelling-to-sound conversion (Damper et al ., 1999).…”

Section: Principles Of Pronunciation By Analogymentioning

confidence: 99%

Multilingual pronunciation by analogy

Soonklang¹,

Damper²,

Marchand

2008

Nat. Lang. Eng.

View full text Add to dashboard Cite

Automatic pronunciation of unknown words (i.e., those not in the system dictionary) is a difficult problem in text-to-speech (TTS) synthesis. Currently, many data-driven approaches have been applied to the problem, as a backup strategy for those cases where dictionary matching fails. The difficulty of the problem depends on the complexity of spelling-to-sound mappings according to the particular writing system of the language. Hence, the degree of success achieved varies widely across languages but also across dictionaries, even for the same language with the same method. Further, the sizes of the training and test sets are an important consideration in data-driven approaches. In this paper, we study the variation of letter-to-phoneme transcription accuracy across seven European languages with twelve different lexicons. We also study the relationship between the size of dictionary and the accuracy obtained. The largest dictionaries of each language have been partitioned into ten approximately equal-sized subsets and combined to give ten different-sized test sets. In view of its superior performance in previous work, the transcription method used is pronunciation by analogy (PbA). Best results are obtained for Spanish, generally believed to have a very regular ('shallow') orthography, and poorest results for English, a language whose irregular spelling system is legendary. For those languages for which multiple dictionaries were available (i.e., French and English), results were found to vary across dictionaries. For the relationship between dictionary size and transcription accuracy, we find that as dictionary size grows, so performance grows monotonically. However, the performance gain decelerates (tends to saturate) as the dictionary increases in size; the relation can simply be described by a logarithmic regression, one parameter of which (α) can be taken as quantifying the depth of orthography of a language. We find that α for a language is significantly correlated with transcription performance on a small dictionary (approximately 10,000 words) for that language, but less so for asymptotic performance. This may be because our measure of asymptotic performance is unreliable, being extrapolated from the fitted logarithmic regression.

show abstract

Information fusion approaches to the automatic pronunciation of print by analogy

Cited by 13 publications

References 26 publications

Automatic Syllabification in English: A Comparison of Different Algorithms

Automatic Syllabification in English: A Comparison of Different Algorithms

A probabilistic approach to pronunciation by analogy

Multilingual pronunciation by analogy

Contact Info

Product

Resources

About