Zobrazeno 1 - 10
of 16
pro vyhledávání: '"Mohammad Reza Selim"'
With the advent of deep learning, Text-to-Speech (TTS) research has made a great leap in producing natural speech. The state-of-the-art TTS systems generate average prosody, resulting in a lack of variety and expressiveness found in human speech. To
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a7f0c8c8470072716868f17a7c2a5958
https://doi.org/10.21203/rs.3.rs-1690533/v1
https://doi.org/10.21203/rs.3.rs-1690533/v1
Publikováno v:
Journal of Computer Science. 16:1128-1138
Publikováno v:
Acoustical Science and Technology. 40:374-381
Autor:
Mohammad Reza Selim, Mohammed Raihan Hussain, Mohammad Shahidur Rahman, Muhammed Zafar Iqbal, Arif Ahmad
Publikováno v:
2018 International Conference on Bangla Speech and Language Processing (ICBSLP).
Extracting pronunciation from written text is necessary in many application areas, especially in text-to-speech synthesis. ‘Bangla’ is not completely a phonetic language, meaning there is not always direct mapping from orthography to pronunciatio
Publikováno v:
2018 International Conference on Bangla Speech and Language Processing (ICBSLP).
Machine Translation has become one of the top research interests for a few years. Compared to others, statistical and neural network approaches toward machine translation are performing the best. However, both approaches have advantages over one anot
Publikováno v:
2018 International Conference on Bangla Speech and Language Processing (ICBSLP).
The speakers' variability caused by accent is one of the key elements that plays role for robust speech recognition. This study investigates accent related variations of acoustic characteristics of four monophthongal vowels of Bangladeshi Bangla lang
Publikováno v:
2018 International Conference on Bangla Speech and Language Processing (ICBSLP).
In this paper a complete and robust segmentation process for printed Bangla script is presented. This phase is important for language like Bangla in which resources are not easily available. In Bangla OCR system, one of the main challenges is charact
Publikováno v:
2018 International Conference on Computer, Communication, Chemical, Material and Electronic Engineering (IC4ME2).
For different areas of Natural Language Processing (NLP) research parallel corpora are an important resource. Parallel corpora aligned at sentence level is more efficient and useful than parallel corpora which are not aligned for various applications
Publikováno v:
Parallel Computing. 40:1-33
There has been a renewed interest in dataflow computing models in recent years of technology scaling. Potentiality of exploiting huge parallelism, with the expense of low power, simpler circuit, less silicon area, is the main characteristic of a data
Autor:
MOHAMMAD, REZA SELIM
Publikováno v:
埼玉大学大学院理工学研究科博士学位論文 : 論文内容の要旨及び論文審査の結果の要旨. 35:42-46
博士の専攻分野の名称: 博士(学術)学位授与年月日: 平成20年9月19日