216 Hits in 3.7 sec

Acoustic Pronunciation Variations Modeling for Standard Malay Speech Recognition

Noraini Seman, Kamaruzaman Jusoff
2008 Computer and Information Science  
This paper presents different methods of handling pronunciation variations in Standard Malay (SM) speech recognition.  ...  Experimental results show that the use of a pronunciation variation dictionary and the method of dynamic search space expansion can improve speech recognition performance substantially.  ...  In this paper, the pronunciation variations in spontaneous Standard Malay (SM) speech are studied.  ... 
doi:10.5539/cis.v1n4p112 fatcat:7nu4q4vzmrggvj36irur36hgyy

Multilingual Speech Evaluation: Case Studies on English, Malay and Tamil [article]

Huayun Zhang, Ke Shi, Nancy F. Chen
2021 arXiv   pre-print
Empirical validations show consistent gains for all three languages when predicting pronunciation, rhythm and intonation performance.  ...  While speech evaluation on English has been popular, automatic speech scoring on low resource languages remains challenging.  ...  Malay and Tamil Acoustic Models: Malay and Tamil acoustic models have the same configuration and were trained on 600 hours' Malay speech (1,500 native speakers from Singapore and Malaysia) and 200 hours  ... 
arXiv:2107.03675v1 fatcat:mfjujvfd55eark4rth5ymxrpw4

Malay Language Speech Recogniser with Hybrid Hidden Markov Model and Artificial Neural Network(HMM/ANN)

H. F. Ong, A. M. Ahmad
2011 International Journal of Information and Education Technology  
In addition to that, this paper presents a study on Standard Malay's phonetic and phonology to help in the recognition of Malay words.  ...  The common hybrid method in speech recognition is the combination of Hidden Markov Model (HMM) and Artificial Neural Network (ANN).  ...  For instance, the phone-level transcription labels the pronunciation for the uttered words by referring to the phonemes for Standard Malay language (see Section II).  ... 
doi:10.7763/ijiet.2011.v1.19 fatcat:w6kj7btmcvbbxbu6dawtapnm6e

PronouncUR: An Urdu Pronunciation Lexicon Generator [article]

Haris Bin Zia, Agha Ali Raza, Awais Athar
2018 arXiv   pre-print
State-of-the-art speech recognition systems rely heavily on three basic components: an acoustic model, a pronunciation lexicon and a language model.  ...  In this paper, we present a grapheme-to-phoneme conversion tool for Urdu that generates a pronunciation lexicon in a form suitable for use with speech recognition systems from a list of Urdu words.  ...  Modern speech recognition systems usually require three resources: transcribed speech for acoustic modeling, a large text data for language modeling and a pronunciation lexicon that maps words to sub-word  ... 
arXiv:1801.00409v2 fatcat:z6462p2pdzfyta6srrhccnnjqm

Unsupervised Feature Adaptation Using Adversarial Multi-Task Training for Automatic Evaluation of Children's Speech

Richeng Duan, Nancy F. Chen
2020 Interspeech 2020  
A front-end feature transformation module is positioned prior to an acoustic model trained on adult speech (1) to leverage on the readily available linguistic resources on adult speech or existing models  ...  Experimental results demonstrate that our proposed approach consistently outperforms established baselines trained on adult speech across a variety of tasks ranging from speech recognition to pronunciation  ...  Experimental results Speech recognition To validate our baseline model (DNN model trained on adult speech), we used the pruned version of the standard Wall Street Journal (WSJ) 5k trigram language model  ... 
doi:10.21437/interspeech.2020-1657 dblp:conf/interspeech/DuanC20 fatcat:fmyri7jmwbazfpsztsc3awihd4

Computational intelligence in processing of speech acoustics: a survey

Amitoj Singh, Navkiran Kaur, Vinay Kukreja, Virender Kadyan, Munish Kumar
2022 Complex & Intelligent Systems  
This paper presents a comprehensive survey on the speech recognition techniques for non-Indian and Indian languages, and compiled some of the computational models used for processing speech acoustics.  ...  This paper examined major challenges for speech recognition for different languages.  ...  handled pronunciation variations in the Standard Malay (SM) system of speech recognition.  ... 
doi:10.1007/s40747-022-00665-1 fatcat:6pu2xccbq5as7bn2y2tav2fdwa

Malay Wordlist Modeling for Articulation Disorder Patient by Using Computerized Speech Diagnosis System

Mohd Nizam Mazenan, Tian-Swee Tan
2014 Research Journal of Applied Sciences Engineering and Technology  
The prototype of the system is already been develop in order to help Speech Therapist (ST) or Speech Language Pathologist (SLP) in diagnosis, preventing and treatment for an early stage.  ...  This study will surveys the technique and method use by ST at Hospital Sultanah Aminah (HSA) (Speech therapist at Speech Therapy Center) to help patient that suffer from speech disorder especially in articulation  ...  Assuming we are using standard Malay phoneme based pronunciation dictionary for our target words, where it has been used to describe the phones HMM acoustic model for the mapping process to form a word  ... 
doi:10.19026/rjaset.7.830 fatcat:tgrrcft6ojelbl6t7j5dj5znvq

Adaptation to Pronunciation Variations in Indonesian Spoken Query-Based Information Retrieval

Dessi Puji LESTARI, Sadaoki FURUI
2010 IEICE transactions on information and systems  
To improve the proper noun recognition accuracy, proper-noun specific acoustic models are created by supervised adaptation using maximum likelihood linear regression (MLLR).  ...  Recognition errors of proper nouns and foreign words significantly decrease the performance of ASR-based speech applications such as voice dialing systems, speech summarization, spoken document retrieval  ...  Acknowledgments The authors would like to thank the ILPS, University of Amsterdam, for giving us the Kompas and Majalah Tempo collections.  ... 
doi:10.1587/transinf.e93.d.2388 fatcat:tdvjapxhxfdcdp3ltr3pkszyke

Investigation of Effects of Different Synthesis Unit to the Quality of Malay Synthetic Speech

Lau Chee Yong, Tan Tian Swee, Mohd Nizam Mazenan
2014 Research Journal of Applied Sciences Engineering and Technology  
In Malay language, the unit size of letter is smaller than phoneme.  ...  Synthesis unit of a speech synthesizer directly affects the computational load and output speech quality. Generally, phoneme is the best choice to synthesize high quality speech.  ...  Centre (RMC) for supporting this research project under RUG grant VOT 00G70.  ... 
doi:10.19026/rjaset.7.737 fatcat:lqb4qw24kjbdjnfzobufffbzza

Jawi Character Speech-to-Text Engine Using Linear Predictive and Neural Network for Effective Reading

Zaini Arifah Othman, Zaidi Razak, Nor Aniza Abdullah, Mohd. Yakub Zulkifli Bin Mohd. Yusoff
2009 2009 Third Asia International Conference on Modelling & Simulation  
However, its pronunciations are in Malay Language. This uniqueness makes STT development a challenging task.  ...  Therefore, it is important to develop tools for teaching kids about Jawi characters and Speech-To-Text (STT) application can serve this purpose well.  ...  Standard Malay itself is a unique language based on its similarities to English and Arabic. Malay is a phonetic language and it is written in two types of character.  ... 
doi:10.1109/ams.2009.94 dblp:conf/asiams/OthmanRAY09 fatcat:u3viw6bkbzefzeart6ojexynii

Developing an HMM-Based Speech Synthesis System for Malay: A Comparison of Iterative and Isolated Unit Training

Mumtaz Begum MUSTAFA, Zuraidah Mohd DON, Raja Noor AINON, Roziati ZAINUDDIN, Gerry KNOWLES
2014 IEICE transactions on information and systems  
This research aims at developing an HMM-based speech synthesis system for Malay.  ...  model of English.  ...  The authors would like to thank the reviewers for their continuous effort in reviewing the manuscript and providing useful comments in order to improve the quality of this manuscript.  ... 
doi:10.1587/transinf.e97.d.1273 fatcat:ywl45evfrra6vnrmocjyicfsne

The Effect Of Changes In Speech Features On The Recognition Accuracy Of ASR System: A Study On The Malay Speech Impaired Children

F. Rosdi, M. B. Mustafa, S. S. Salim, B.A. Hamid
2017 Malaysian Journal of Computer Science  
This paper explains the differences between impaired speeches and non-impaired speeches that can be used in developing automated speech recognition system.  ...  As there is no existing speech database for performing the evaluation, we have developed a speech database of speech impaired children and have analysed the impaired speech features.  ...  We have used the triphone Hidden Markov Models (HMMs) acoustic models to study the effect on the word and phoneme level recognition.  ... 
doi:10.22452/mjcs.vol30no1.4 fatcat:63nro3cuxfgjhnuvrr3em5osoy

An Improved Feature Extraction Method for Malay Vowel Recognition based on Spectrum Delta

Shahrul Azmi M.Y.
2014 International Journal of Software Engineering and Its Applications  
Malay speech recognition is becoming popular among Malaysian researchers.  ...  In Malaysia, more local researchers are focusing on noise robust and accurate independent speaker speech recognition systems that use Malay language.  ...  Appreciation is also given to Tadika Tunku Puteri Intan Shafinaz for providing the valuable speech data.  ... 
doi:10.14257/ijseia.2014.8.1.35 fatcat:2ktwpxx4p5chzdy6sh5z3t27gy

Hybrid methods of brandt's generalised likelihood ratio and short-term energy for malay word speech segmentation

Noraini Seman, Ahmad Firdaus Norazam
2019 Indonesian Journal of Electrical Engineering and Computer Science  
<p>Speech segmentation is an important part for speech recognition, synthesizing and coding.  ...  Experimental results show on average 80% accuracy with 0.2 second time tolerance for automatic segmentation with the algorithm having no knowledge of the acoustic characteristics. </p>  ...  ACKNOWLEDGEMENTS The authors would like to thank Universiti Teknologi MARA (UiTM) for the research funding and support via grant number 600-IRMI/PERDANA 5/3 BESTARI (107/2018).  ... 
doi:10.11591/ijeecs.v16.i1.pp283-291 fatcat:askeuig2ufc6jh7bidash7hoyy

A Systematic Approach for Malay Language Dialect Identification by Using CNN

Mohd Azman Hanif Sulaiman, Nurhakimah Abd Aziz, Azlee Zabidi, Zuraidah Jantan, Ihsan Mohd Yassin, Megat Syahirul Amin Megat Ali
2021 International Journal of Electrical & Electronic Systems Research (IEESR)  
Speech recognition systems need to be robust to cater for various languages and dialects in order to interact better with humans.  ...  Dialects within a spoken language present a challenge for computers require a speech recognition system to translate these verbal commands to computer understanding of the underlying meaning from spoken  ...  This paper focus is on Malay pronunciation and phonology.  ... 
doi:10.24191/jeesr.v19i1.004 fatcat:6xjqdfb4ajbahlzxuexfh46bxu
« Previous Showing results 1 — 15 out of 216 results