Corpus ID: 3667433

PronouncUR: An Urdu Pronunciation Lexicon Generator

@article{Zia2018PronouncURAU,
  title={PronouncUR: An Urdu Pronunciation Lexicon Generator},
  author={Haris Bin Zia and Agha Ali Raza and Awais Athar},
  journal={ArXiv},
  year={2018},
  volume={abs/1801.00409}
}
State-of-the-art speech recognition systems rely heavily on three basic components: an acoustic model, a pronunciation lexicon and a language model. To build these components, a researcher needs linguistic as well as technical expertise, which is a barrier in low-resource domains. Techniques to construct these three components without having expert domain knowledge are in great demand. Urdu, despite having millions of speakers all over the world, is a low-resource language in terms of standard… Expand
Automatic Pronunciation Generator for Indonesian Speech Recognition System Based on Sequence-to-Sequence Model
  • Devin Hoesen, Fanda Yuliana Putri, D. Lestari
  • Computer Science
  • 2019 22nd Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)
  • 2019
TLDR
This paper employs a sequence-to-sequence (seq2seq) approach to generate pronunciation for each word in an Indonesian dictionary and demonstrates that by using this approach, it can obtain a similar speech-recognition error-rate while requiring only a fractional amount of resource. Expand
SEMOUR: A Scripted Emotional Speech Repository for Urdu
TLDR
SEMOUR is presented, the first scripted database of emotion-tagged speech in the Urdu language, to design an Urdu Speech Recognition System, and correctly predicts an emotion with a state-of-the-art 92% accuracy. Expand
Rapid Collection of Spontaneous Speech Corpora Using Telephonic Community Forums
TLDR
A novel technique for rapid collection of spontaneous speech data over mobile phone channel using telephonic community forums, especially useful for gathering speech corpora for underresourced languages hence enabling the development of speech recognition, keyword spotting, speaker ID, and noise classification systems for such languages. Expand

References

SHOWING 1-10 OF 36 REFERENCES
Discriminative pronunciation learning for speech recognition for resource scarce languages
TLDR
A method to create speech recognition capability for small vocabularies in resource-scarce languages, which means languages that have a small or economically disadvantaged user base which are typically ignored by the commercial world is described. Expand
TTS for Low Resource Languages: A Bangla Synthesizer
TLDR
A process for streamlining the bootstrapping of TTS systems for under-resourced languages by using crowdsourcing to collect data from multiple ordinary speakers and employing statistical techniques to construct multi-speaker acoustic models using Long Short-Term Memory Recurrent Neural Network and Hidden Markov Model approaches is proposed. Expand
GlobalPhone: Pronunciation Dictionaries in 20 Languages
TLDR
The advances in the multilingual text and speech database GlobalPhone, a multilingual database of high-quality read speech with corresponding transcriptions and pronunciation dictionaries in 20 languages, are described. Expand
Using a hybrid approach to build a pronunciation dictionary for Brazilian Portuguese
TLDR
The method employed to build a machinereadable pronunciation dictionary for Brazilian Portuguese makes use of a hybrid approach for converting graphemes into phonemes, based on both manual transcription rules and machine learning algorithms. Expand
Letter-to-Sound Conversion for Urdu Text-to-Speech System
TLDR
Urdu pronunciation may be modelled from Urdu text by defining fairly regular rules, and these rules have been identified and explained in this paper. Expand
Low-resource speech translation of Urdu to English using semi-supervised part-of-speech tagging and transliteration
TLDR
The construction of a semi-supervised HMM-based part-of-speech tagger that is used to train factored translation models and the use of an H MM-based transliterator from which to derive a spelling-to-pronunciation model for Urdu used in ASR training are described. Expand
Grapheme-to-phoneme transcription rules for Spanish, with application to automatic speech recognition and synthesis
TLDR
A letter-to-phone conversion system for Spanish designed to supply transcriptions to the flexible vocabulary speech recogniser and to the synthesiser, both developed at CSELT, Turin, Italy, with different sets of rules designed for the two applications. Expand
A Corpus and Phonetic Dictionary for Tunisian Arabic Speech Recognition
TLDR
An effort to create a corpus and phonetic dictionary for Tunisian Arabic Automatic Speech Recognition (ASR) by defining a set of pronunciation rules and a lexicon of exceptions and evaluating the performance of these rules on two types of corpora. Expand
Small-vocabulary speech recognition for resource-scarce languages
TLDR
An off-the-shelf commercial speech recognizer is used, which is trained extensively on a resource-rich language such as English, to derive phonemic representations for any desired word in any target language by a process of cross-language phonemic mapping. Expand
Sequence-to-sequence neural net models for grapheme-to-phoneme conversion
TLDR
The simple side-conditioned generation approach is able to rival the state-of-the-art with bi-directional long short-term memory (LSTM) neural networks that use the same alignment information that is used in conventional approaches. Expand
...
1
2
3
4
...