Acoustic Characterization of Amharic Vowel Sound Units
Pages 36 - 40
Abstract
Acoustic characterization of vowels has a significant role in the development of speech synthesis and recognition systems. Specifically, it reduces the improper vowel parameter selection for the concatenative and formant based speech synthesis systems. This paper studies the acoustic characteristics of Amharic vowel sound units. The characteristics of Amharic vowels are studied by considering 77 different contexts. All the seven vowels are labeled from different contexts, and then the first three formant frequencies (F1, F2, and F3) and duration acoustic features are extracted and analyzed for all vowels to characterize their quality and quantity behaviors. As a result, this study synthesizes the acoustic vowel space diagram by graphically illustrating where vowel sound units for the Amharic language are located in the acoustic space of the vocal tract tube. The effect of duration on the formant frequency values and the comparison of vowels via duration behavior are also investigated. The characterization demonstrates that F1 is inversely proportional to duration, while F2 and F3 are directly proportional to duration, and the vowels /e/, /a/, and /o/ are the long vowels, while /ix/ is a short vowel.
References
[1]
Ali, A., Bhatti, S., and Mian, M.S. 2006. Formants Based Analysis for Speech Recognition. In Proceedings of IEEE International Conference on Engineering of Intelligent Systems (Islamabad, Pakistan, April 22-23, 2006). IEEE, 1--3. DOI= https://doi.org/10.1109/ICEIS.2006.1703179
[2]
Alotaibi1, Y.A., and Hussain, A. 2010. Comparative Analysis of Arabic Vowels using Formants and an Automatic Speech Recognition System. International Journal of Signal Processing, Image Processing and Pattern Recognition Processing and Pattern Recognition. 3, 2, 11--22.
[3]
Boersma, P. and Weenink D. 2018. Praat: doing phonetics by computer. Version 6.0.26, retrieved 14 March 2018 from http://www.praat.org/.
[4]
Esfandiari, N., Alinezhad, B., and Rafiei, A. 2015. Vowel Classification and Vowel space in Persian. Theory and practice in language studies. 5, 2, 426--434.
[5]
Fantaye, T.G. 2011. Characterization of Amharic vowel sound units. M.Sc. Thesis, Addis Ababa University, Addis Ababa, Ethiopia.
[6]
H/Mariam, S., Kishore, S.P., Black, A.W., Kumar, R., and Sangal, R. 2005. Unit Selection Voice for Amharic using Festivox. 5th ISCA Speech Synthesis Workshop. Pittsburgh, 103--107.
[7]
Harrington, J. and Cassidy, S. 1999. Techniques in Speech Acoustics. Kluwer Academic Publishers, Text, Speech and Language Technology Series. Dordrecht, the Netherlands.
[8]
Hillenbrand, J.M., Getty, L.A., Clark, M. J., and Wheeler K. 1995. Acoustic characteristics of American English vowels. The Journal of the Acoustical Society of America. 97, 5, 3099--3111.
[9]
Hossain, S.A., Rahman, M.L., and Ahmed, F. 2005. Acoustic Space of Bangla Vowels. In Proceedings of the 5th WSEAS Int. Conf. on signal, speech and image processing. Corfu, Greece, August 17-19, 138--142.
[10]
Hossain, S.A., Rahman, M.L., and Ahmed F. 2007. Bangla Vowel Characterization based on Analysis by Synthesis. International Journal of Electronics and Communication Engineering. 1, 2, 373--376.
[11]
Iwatsuki, S. 2011. An acoustic Observation on 1st and 4th Order Vowels of Amharic. In Cushitic-Omotic Studies 2010, Yoichi TSUGE and Hideyuki INUI Ed.
[12]
Iwatsuki, S. 2012. An Acoustic Analysis of Amharic Vowels. Nagoya University, Unpublished.
[13]
Kasie, E.B., and Assabie, Y. 2012. Concatenative Speech Synthesis for Amharic Using Unit Selection Method. In proceedings of International ACM Conference on MEDES (Addis Ababa, Ethiopia, October 28-31, 2012), ACM, New York, NY, USA, 27--31. DOI=https://doi.org/10.1145/2457276.2457282.
[14]
Kent, R.D. and Vorperian, H.K, 2018. Static measurements of vowel formant frequencies and bandwidths: A review. Journal of Communication Disorders. 74, 74--97.
[15]
Lukose, S. and Upadhya, S.S. 2017. Text to Speech Synthesizer-Formant Synthesis. In proceedings of 2017 International Conference on Nascent Technologies in the Engineering Field (ICNTE). Navi Mumbai, India, 1--4.
[16]
Martinez, F., Guillamon, A., and Martinez, J.J. 2003. Vowel and Consonant Characterization using fractal dimension in natural speech. ISCA None-Linear Speech Production and Characterization Workshop. Spain, 1--4.
[17]
Mekonnen A.M. 2013. Speech Production in Amharic-Speaking Children with Repaired Cleft Palatal. Ph.D. Thesis, University of Sheffield, Sheffield, England.
[18]
Mergia, N.T. 2008. Formant based speech synthesis for Amharic vowels. M.Sc. Thesis, Addis Ababa University, Addis Ababa, Ethiopia.
[19]
Neumeyer, V., Harrington, J., and Draxler, C. 2010. An acoustic analysis of the vowel space in young and old cochlear-implant speakers. Journal of Clinical Linguistics and Phonetics. 24, 9, 734--741.
[20]
Peterson, G.E and Barney, H.L. 1952. Control methods used in a study of the vowels. The Journal of the Acoustical Society of American. 24, 2, 175--184.
[21]
SIL International. 2012. Speech Analyzer. Version 3.1, retrieved 14 March 2018 from http://www.sofware.sil.org/speech-analyer/.
[22]
Tafere, Y. 2008. Formant-based speech synthesis: A case of Amharic words. M.Sc. Thesis, Addis Ababa University, Addis Ababa, Ethiopia.
[23]
Toledano, D.T., Fernandez-Gallego, M.P., and Lozano-Diez, A. 2018. Multiresolution speech analysis for automatic speech recognition using deep neural networks: Experiments on TIMIT. PLoS ONE 13(10): e0205355. https://doi.org/10.1371/journal.pone.0205355.
[24]
Worku H.S. 2011. Acoustic characterization of glottal stop and glottalized sounds in Amharic using none-spectral methods of speech analysis. Ph.D. Thesis, International Institute of Technology, Hyderabad, India.
Index Terms
- Acoustic Characterization of Amharic Vowel Sound Units
Recommendations
Spotting glottal stop in Amharic in continuous speech
Glottal stop sounds in Amharic are produced due to abrupt closure of the glottis without any significant gesture in the accompanying articulatory organs in the vocal tract system. It is difficult to observe the features of the glottal stop through ...
Using different acoustic, lexical and language modeling units for ASR of an under-resourced language - Amharic
State-of-the-art large vocabulary continuous speech recognition systems use mostly phone based acoustic models (AMs) and word based lexical and language models. However, phone based AMs are not efficient in modeling long-term temporal dependencies and ...
Speech recognition system based on deep neural network acoustic modeling for low resourced language-Amharic
ICTCE '19: Proceedings of the 3rd International Conference on Telecommunications and Communication EngineeringIn this paper automatic speech recognition is investigated using deep neural network (DNN) acoustic modeling method for Amharic language at syllabic acoustic units. In grapheme based database; graphemes/characters are basic units of lexicon and language ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
September 2019
188 pages
ISBN:9781450362412
DOI:10.1145/3364908
Copyright © 2019 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
In-Cooperation
- Beijing University of Posts and Telecommunications
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 20 September 2019
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Funding Sources
- National Natural Science Foundation of China
Conference
SSPS 2019
SSPS 2019: 2019 International Symposium on Signal Processing Systems
September 20 - 22, 2019
Beijing, China
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 83Total Downloads
- Downloads (Last 12 months)15
- Downloads (Last 6 weeks)3
Reflects downloads up to 06 Feb 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in