Acoustic models comparison using HTK and the Spoltech corpus to Brazilian Portuguese
Authors: 
Yuri T. Passos, Carlos A. F. Pimentel Filho, Uriel Marx C. Bispo, Leonardo Nogueira MatosAuthors Info & Claims
Article No.: 37, Pages 1 - 4
Abstract
This paper shows a comparison between Hidden Markov Models (HMM) trained with 12 mel-cepstral coefficients plus extra(s) parameter(s) and two different HMM initialization ways. Thus, it compares the models, in order to detect the more robust parameter added to the mel-cepstral vector in an Automatic Speech Recognizer (ASR) system for the Brazilian Portuguese. To perform such experiments, it uses the HTK to train the HMMs. All the HMMs models used the same speech training base, which is the Spoltech corpus.
References
[1]
}}José A. Martins Avaliação de diferentes Técnicas para reconhecimento de fala. Tese (doutorado), Universidade Estadual de Campinas, Faculdade de Engenharia Elétrica e de Computação, 1997.
[2]
}}Steve Young et al. The HTK Book. Cambridge University Engineering Dept, p. 358, 2006.
[3]
}}Mauricio C. Schramm et al. SPOLTECH: Advancing Human Language Technology in Brazil and the United States Through collaborative Research on Portuguese Spoken Language Systems. Universidade Federal do Rio Grande do Sul: Instituto de Informática. Relatório Técnico. 2001.
[4]
}}Siravenha, Ana Carolina et al. Uso de regras fonológicas com determinação de vogal tônica para conversão grafemafone em português brasileiro. In: Anais do 7th International Information and Telecommunication Technologies Symposium - I2TS 2008, 2008, Foz do Iguaçu. I2TS 2008, 2008.
[5]
}}Linguistic Data Consortium (LDC). "http://www.ldc.upenn.edu/Catalog/CatalogEntry.jsp?catalog Id=LDC2006S16" Visitado em junho de 2009.
[6]
}}Libsndfile. http://www.mega-nerd.com/libsndfile/. Visitado em junho de 2009.
[7]
}}Carlos Patrick Alves da Silva. Sistemas de reconhecimento de voz para o português brasileiro utilizando os corpora Spoltech e OGI-22. Trabalho de conclusão de curso. Universidade Federal do Pará, 2008.
[8]
}}Carlos Alberto Ynoguti. Reconhecimento de fala contínua usando Modelos Ocultos de Markov. Tese (doutorado), Universidade Estadual de Campinas, Faculdade de Engenharia Elétrica e de Computação, 1999.
[9]
}}Rafael Teruszkin Tevah. Implementação de um sistema de reconhecimento de fala contínua com amplo vocabulário para o português brasileiro. Dissertação (mestrado). COPPE/UFRJ, M.Sc., Engenharia Elétrica, 2006.
[10]
}}Spaans M. A. On Develop Acoustic Models Using HTK. Master (Thesis) Faculty of Eletrical Engineering, Mathematics and Computer Science. Delft University of Technology, 2004.
[11]
}}John R. Deller, John H. L. Hansen, John G. Proakis. Discrete time processing of speech signals. Wiley-IEEE Press, 1999.
[12]
}}Evandro Gouvea et al. Sphinx 4 for the JavaTM platform Architecture Notes. "http://www.speech.cs.cmu.edu/sphinx/twiki/pub/Sphinx4/WebHome/Architecture.pdf". Visitado em junho de 2009.
Index Terms
- Acoustic models comparison using HTK and the Spoltech corpus to Brazilian Portuguese
Recommendations
A comparative study of different features for isolated spoken word recognition using HMM with reference to Assamese language
This paper describes the work done in implementation of speaker independent, isolated word recognizer for Assamese language. Linear predictive coding (LPC) analysis, LPC cepstral coefficients (LPCEPSTRA), linear mel-filter bank channel outputs and mel ...
Development and Analysis of Speech Recognition Systems for Assamese Language Using HTK
Language analysis is very important for the native speaker to connect with the digital world. Assamese is a relatively unexplored language. In this report, we analyze different aspects of speech-to-text processing, starting from building a speech corpus, ...
A Comparison between HTK and SPHINX on Chinese Mandarin
JCAI '09: Proceedings of the 2009 International Joint Conference on Artificial IntelligenceIn order to show the performances between different speech recognition engines in Chinese Mandarin recognition, experiments are designed in this paper to compare the recognition performances on Chinese Mandarin between HTK and Sphinx, which are the two ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
October 2009
382 pages
ISBN:9781605588803
DOI:10.1145/1858477
- Conference Chairs:
- Fernando Antonio Mota Trinta,
- Pedro Porfírio,
- Program Chairs:
- Rudinei Goularte,
- Renata Pontin de Mattos Fortes
Copyright © 2009 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]
Sponsors
- SBC: Brazilian Computer Society
In-Cooperation
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 05 October 2009
Check for updates
Author Tags
Qualifiers
- Short-paper
Conference
WebMedia '09
Sponsor:
- SBC
WebMedia '09: XV Brazilian Symposium on Multimedia and the Web
October 5 - 7, 2009
Ceará, Fortaleza, Brazil
Acceptance Rates
Overall Acceptance Rate 270 of 873 submissions, 31%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 90Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 11 Dec 2024
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