Rule-Based Automatic Phonetic Transcription for the Romanian Language

Toma, Stefan-Adrian; Munteanu, Doru-Petru

doi:10.1109/computationworld.2009.59

Cited by 12 publications

(3 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If the word is located in the dictionary, the system generates the corresponding phonetic transcription as the output. Conversely, if the word is not found, it is forwarded to the Phonetic converter block where each letter is sequentially transformed into its respective phonetic repre-sentation [28]. Within the realm of data-driven methodologies, the decision tree algorithm emerges as an uncomplicated and efficient approach.…”

Section: Lenition Phenomenonmentioning

confidence: 99%

WITHDRAWN: Integrating Prior Knowledge and Data-Driven Approaches for Improving Grapheme-to-Phoneme Conversion in Korean Language

Cao,

Zhao,

2023

Preprint

View full text Add to dashboard Cite

Currently, grapheme-to-phoneme (G2P) conversion technology is dominated by two methodologies: knowledge-based and data-based approaches. Knowledge-driven methods face challenges in adapting to extensive datasets, while data-driven methods heavily rely on high-quality data and require precise feature selection for model construction. To overcome these challenges, this research proposes an integrated approach that combines prior knowledge with data-driven techniques for automatic G2P conversion in the Korean language. We extract attributes based on pronunciation rules and phonetic transformations between Korean words to construct a decision tree. Subsequently, the model is trained using the data-driven approach for automated phonetic transcription. The proposed model achieves more accurate alignment between input and output variables, effectively capturing phonological variations in continuous Korean speech and determining corresponding phonemes for graphemes. Rigorous cross-validation confirms its superiority, with an average accuracy of 94.63% in grapheme-to-phoneme conversion, outperforming existing methodologies.

show abstract

Section: Lenition Phenomenonmentioning

confidence: 99%

WITHDRAWN: Integrating Prior Knowledge and Data-Driven Approaches for Improving Grapheme-to-Phoneme Conversion in Korean Language

Cao,

Zhao,

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…For Romanian, the three lexical tasks were also subject to a series of studies covering Marcus Contextual Grammars (Dinu 2003), rule-based methods (Toma andMunteanu 2009), decision trees and linear models (Cucu et al 2014), cascaded sequential models Dinu et al 2014) or neural network-based approaches (Boroş, Dumitrescu, and Pais 2018;Stan and Giurgiu 2018;Stan 2019Stan , 2020. The reported WER for stress prediction is 2.36%, while the reported WERs for the phonemic transcription are between 1% and 3%.…”

Section: The Romanian Language and Romanian Lexical Datasetsmentioning

confidence: 99%

RoLEX: The development of an extended Romanian lexical dataset and its evaluation at predicting concurrent lexical information

et al. 2022

View full text Add to dashboard Cite

In this article, we introduce an extended, freely available resource for the Romanian language, named RoLEX. The dataset was developed mainly for speech processing applications, yet its applicability extends beyond this domain. RoLEX includes over 330,000 curated entries with information regarding lemma, morphosyntactic description, syllabification, lexical stress and phonemic transcription. The process of selecting the list of word entries and semi-automatically annotating the complete lexical information associated with each of the entries is thoroughly described. The dataset’s inherent knowledge is then evaluated in a task of concurrent prediction of syllabification, lexical stress marking and phonemic transcription. The evaluation looked into several dataset design factors, such as the minimum viable number of entries for correct prediction, the optimisation of the minimum number of required entries through expert selection and the augmentation of the input with morphosyntactic information, as well as the influence of each task in the overall accuracy. The best results were obtained when the orthographic form of the entries was augmented with the complete morphosyntactic tags. A word error rate of 3.08% and a character error rate of 1.08% were obtained this way. We show that using a carefully selected subset of entries for training can result in a similar performance to the performance obtained by a larger set of randomly selected entries (twice as many). In terms of prediction complexity, the lexical stress marking posed most problems and accounts for around 60% of the errors in the predicted sequence.

show abstract

“…The difficulty of the linguistic processing varies according to the language considered. The Arabic language is less difficult to transcribe phonetically than many other languages such as European languages (Braga et al 2006;Stefan-Adrian and Doru-Petru 2009). This is due to the fact that the orthographic form of Arabic language is close to its phonetic form.…”

mentioning

confidence: 99%

Development of an automatic phonetization system for Arabic text-to-speech synthesis

Imedjdouben

Houacine

2014

Int J Speech Technol

View full text Add to dashboard Cite

The goal of this paper is to solve the phonetization task of the Arabic text dedicated to text-to-speech synthesis. In this paper, we will describe the steps we followed in order to develop an automatic phonetization system, and the various established rules of phonemic and phonetic transcription. Our text phonetization system is entirely based on a representation according to the Unicode standard, and is divided into two parts. The first part concerns the graphemephoneme transcription that combines use of a lexicon of exceptions, and a base of phonemic transcription rules. The second part concerns the generation of allophones by applying phonetic transcription rules to the phonemes obtained from the grapheme-phoneme transcription. The whole system performs an automatic phonetization for Arabic text-tospeech synthesis.

show abstract

Rule-Based Automatic Phonetic Transcription for the Romanian Language

Cited by 12 publications

References 2 publications

WITHDRAWN: Integrating Prior Knowledge and Data-Driven Approaches for Improving Grapheme-to-Phoneme Conversion in Korean Language

WITHDRAWN: Integrating Prior Knowledge and Data-Driven Approaches for Improving Grapheme-to-Phoneme Conversion in Korean Language

RoLEX: The development of an extended Romanian lexical dataset and its evaluation at predicting concurrent lexical information

Development of an automatic phonetization system for Arabic text-to-speech synthesis

Contact Info

Product

Resources

About