Grapheme-to-phoneme model generation for Indo-European languages

Schlippe, Tim; Ochs, Sebastian; Schultz, Tanja

doi:10.1109/icassp.2012.6288993

Cited by 21 publications

(12 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For languages with highly transparent orthographies such as Spanish or German (Goswani, 1999), g2p approaches typically work quite well (Schlippe et al, 2012). However, for languages with less transparent orthographies, such as English or French (Goswani, 1999), it is relatively difficult to derive simple mappings from the grapheme representation of a syllable to its phoneme representation.…”

Section: Phonetisaurusmentioning

confidence: 99%

See 1 more Smart Citation

MediaParl: Bilingual mixed language accented speech database

Imseng

Bourlard

Caesar

et al. 2012

2012 IEEE Spoken Language Technology Workshop (SLT)

View full text Add to dashboard Cite

MediaParl is a Swiss accented bilingual database containing recordings in both French and German as they are spoken in Switzerland. The data were recorded at the Valais Parliament. Valais is a bilingual Swiss canton with many local accents and dialects. Therefore, the database contains data with high variability and is suitable to study multilingual, accented and non-native speech recognition as well as language identification and language switch detection.We also define monolingual and mixed language automatic speech recognition and language identifictaion tasks and evaluate baseline systems.The database is publicly available for download.

show abstract

Section: Phonetisaurusmentioning

confidence: 99%

“…However, for languages with less transparent orthographies, such as English or French (Goswani, 1999), it is relatively difficult to derive simple mappings from the grapheme representation of a syllable to its phoneme representation. Therefore, g2p approaches tend to work less well (Schlippe et al, 2012).…”

Section: Phonetisaurusmentioning

confidence: 99%

MediaParl: Bilingual mixed language accented speech database

Imseng

Bourlard

Caesar

et al. 2012

2012 IEEE Spoken Language Technology Workshop (SLT)

View full text Add to dashboard Cite

show abstract

“…They are used to train the systems by de scribing the pronunciation of words according to manageable units, typically phonemes [4]. Dictionaries can also be used to build generalized grapheme-to-phoneme (g2p) models, for the purpose of providing pronunciations for words that do not appear in the dictionary [5]. The production of dictionaries can be time-consuming and expensive if they are manually written by language experts.…”

Section: Introductionmentioning

confidence: 99%

Rapid bootstrapping of a Ukrainian large vocabulary continuous speech recognition system

Schlippe

Volovyk

Yurchenko

et al. 2013

2013 IEEE International Conference on Acoustics, Speech and Signal Processing

Self Cite

View full text Add to dashboard Cite

We report on our efforts toward an LVCSR system for the Slavic language Ukrainian. We describe the Ukrainian text and speech database recently collected as a part of our Glob alPhone corpus [1] with our Rapid Language Adaptation Toolkit [2]. The data was complemented by a large collec tion of text data crawled from various Ukrainian websites.For the production of the pronunciation dictionary, we inves tigate strategies using grapheme-to-phoneme (g2p) models derived from existing dictionaries of other languages, thereby reducing severely the necessary manual effort. Russian and Bulgarian g2p models even decrease the number of pronunci ation rules to one fifth. We achieve significant improvement by applying state-of-the art techniques for acoustic modeling and our day-wise text collection and language model interpo lation strategy [3]. Our best system achieves a word error rate of 11.21 % on the test set on read newspaper speech.

show abstract

“…Recently, methods have been proposed that employ pronunciations from the collective knowledge on the World Wide Web as training data for g2p models without a crosscheck of language experts [17]. In this case, the training data is expected to include a lot of noisy data, and empirically, in [17], this degrades the performance of the speech recognition system in exchange for improvements of cost and time required for dictionary construction.…”

Section: Introductionmentioning

confidence: 99%

“…In this case, the training data is expected to include a lot of noisy data, and empirically, in [17], this degrades the performance of the speech recognition system in exchange for improvements of cost and time required for dictionary construction. When this sort of noisy data is used to train a g2p system, it is extremely important to have an approach that is highly accurate and robust to overfitting.…”

Section: Introductionmentioning

confidence: 99%

Structured Adaptive Regularization of Weight Vectors for a Robust Grapheme-to-Phoneme Conversion Model

Kubo

Sakti

Neubig

et al. 2014

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYGrapheme-to-phoneme (g2p) conversion, used to estimate the pronunciations of out-of-vocabulary (OOV) words, is a highly important part of recognition systems, as well as text-to-speech systems. The current state-of-the-art approach in g2p conversion is structured learning based on the Margin Infused Relaxed Algorithm (MIRA), which is an online discriminative training method for multiclass classification. However, it is known that the aggressive weight update method of MIRA is prone to overfitting, even if the current example is an outlier or noisy. Adaptive Regularization of Weight Vectors (AROW) has been proposed to resolve this problem for binary classification. In addition, AROW's update rule is simpler and more efficient than that of MIRA, allowing for more efficient training. Although AROW has these advantages, it has not been applied to g2p conversion yet. In this paper, we first apply AROW on g2p conversion task which is structured learning problem. In an evaluation that employed a dataset generated from the collective knowledge on the Web, our proposed approach achieves a 6.8% error reduction rate compared to MIRA in terms of phoneme error rate. Also the learning time of our proposed approach was shorter than that of MIRA in almost datasets. key words: g2p conversion, out-of-vocabulary word, online discriminative training, structured learning, AROW

show abstract

Grapheme-to-phoneme model generation for Indo-European languages

Cited by 21 publications

References 7 publications

MediaParl: Bilingual mixed language accented speech database

MediaParl: Bilingual mixed language accented speech database

Rapid bootstrapping of a Ukrainian large vocabulary continuous speech recognition system

Structured Adaptive Regularization of Weight Vectors for a Robust Grapheme-to-Phoneme Conversion Model

Contact Info

Product

Resources

About