Publicações

@inproceedings{Batista18b,
    abstract  = {Kaldi has become a very popular toolkit for automatic speech recognition, showing considerable improvements through the combination of hidden Markov models (HMM) and deep neural networks (DNN). However, in spite of its great performance for some languages (e.g. English, Italian, Serbian, etc.), the resources for Brazilian Portuguese (BP) are still quite limited. This work describes what appears to be the first attempt to create Kaldi-based scripts and baseline acoustic models for BP using Kaldi tools. Experiments were carried out for dictation tasks and a comparison to CMU Sphinx toolkit in terms of word error rate (WER) was performed. Results seem promising, since Kaldi achieved the absolute lowest WER of 4.75% with HMM-DNN and outperformed CMU Sphinx even when using Gaussian mixture models only.},
    author    = {Cassio Batista and Ana Larissa Dias and Nelson {Sampaio Neto}},
    booktitle = {Proc. IberSPEECH 2018},
    doi       = {10.21437/IberSPEECH.2018-17},
    pages     = {77--81},
    title     = {Baseline Acoustic Models for Brazilian Portuguese Using Kaldi Tools},
    url       = {http://dx.doi.org/10.21437/IberSPEECH.2018-17},
    year      = {2018}
}

@inproceedings{Batista14,
    author    = {Cassio Batista and Thiago Coelho and Bruno Haick and Nelson Neto and Aldebaro Klautau},
    booktitle = {XIX International Scientific Conference for Young Engineers},
    location  = {Cluj-Napoca, Romania},
    title     = {{LaPS CSR}: A Free Distributed Cloud Speech Recognition System},
    url       = {http://hdl.handle.net/10598/28297},
    year      = {2014}
}

@inproceedings{Batista13,
    author    = {Cassio Batista and Thiago Coelho and Bruno Haick and Nelson Neto and Aldebaro Klautau},
    booktitle = {XXXI Brazilian Telecommunications Symposium},
    location  = {Fortaleza, Brazil},
    title     = {Desenvolvimento e Compara\c{c}\~{a}o De Reconhecedores De Fala Embarcados e Distribu\'{i}dos Para Android},
    url       = {http://gestao.sbrt.org.br/simposios/artigo/visualizar/a/325},
    doi       = {10.14209/sbrt.2013.219},
    year      = {2013}
}

@article{rafael12,
    author    = {Rafael Oliveira and Pedro Batista and Nelson Neto and Aldebaro Klautau},
    journal   = {12th International Conference on Computational Processing of the Portuguese Language},
    pages     = {375-380},
    title     = {Baseline Acoustic Models for {B}razilian {P}ortuguese Using {CMU} Sphinx Tools},
    year      = {2012}
}

@article{Monte11,
    author    = {A. Monte and D. Ribeiro and N. Neto and R. Cruz and A. Klautau},
    journal   = {17th International Congress of Phonetic Sciences},
    pages     = {1418-1421},
    title     = {A Rule-based Syllabification Algorithm with Stress Determination for {B}razilian {P}ortuguese Natural Language Processing},
    year      = {2011}
}

@article{Neto10,
    author    = {Nelson Neto and Carlos Patrick and Aldebaro Klautau and Isabel Trancoso},
    journal   = {Journal of the Brazilian Computer Society},
    pages     = {53-68},
    title     = {Free tools and resources for {B}razilian {P}ortuguese speech recognition},
    volume    = {17},
    year      = {2011}
}

@article{Neto11,
    abstract  = {An automatic speech recognition system has modules that depend on the language and, while there are many public resources for some languages (e.g., English and Japanese), the resources for Brazilian Portuguese (BP) are still limited. This work describes the development of resources and free tools for BP speech recognition, consisting of text and audio corpora, phonetic dictionary, grapheme-to-phone converter, language and acoustic models. All of them are publicly available and, together with a proposed application programming interface, have been used for the development of several new applications, including a speech module for the OpenOffice suite. Performance tests are presented, comparing the developed BP system with a commercial software. The paper also describes an application that uses synthesis and speech recognition together with a natural language processing module dedicated to statistical machine translation. This application allows the translation of spoken conversations from BP to English and vice versa. The resources make easier the adoption of BP speech technologies by other academic groups and industry.},
    author    = {Neto, Nelson and Patrick, Carlos and Klautau, Aldebaro and Trancoso, Isabel},
    day       = {01},
    doi       = {10.1007/s13173-010-0023-1},
    issn      = {1678-4804},
    journal   = {Journal of the Brazilian Computer Society},
    month     = {Mar},
    number    = {1},
    pages     = {53--68},
    title     = {Free tools and resources for Brazilian Portuguese speech recognition},
    url       = {https://doi.org/10.1007/s13173-010-0023-1},
    volume    = {17},
    year      = {2011}
}

@article{rafael11,
    author    = {Rafael Oliveira and Pedro Batista and Nelson Neto and Aldebaro Klautau},
    journal   = {XII Workshop de Software Livre},
    title     = {Recursos para Desenvolvimento de Aplicativos com Suporte a Reconhecimento de Voz para Desktop e Sistemas Embarcados},
    year      = {2011}
}

@article{Pedro10propor,
    author    = {Pedro Batista and Patrick Silva and Nelson Neto and Aldebaro Klautau},
    journal   = {The International Conference on Computational Processing of Portuguese - Demos Session},
    title     = {A non-Visual Web-Browsing System using Speech Recognition for {B}razilian {P}ortuguese},
    year      = {2010}
}

@article{Igor10,
    author    = {I. Couto and N. Neto and V. Tadaiesky and A. Klautau and R. Maia},
    journal   = {7th International Telecommunications Symposium},
    title     = {An Open Source {HMM}-based Text-to-Speech System for {B}razilian {P}ortuguese},
    year      = {2010}
}

@article{Patrick10,
    author    = {Patrick Silva and Pedro Batista and Nelson Neto and Aldebaro Klautau},
    journal   = {Computational Processing of the Portuguese Language},
    pages     = {128-131},
    title     = {An Open-Source Speech Recognizer for {B}razilian {P}ortuguese with a Windows Programming Interface},
    volume    = {6001},
    year      = {2010}
}

@article{denise10,
    author    = {Denise Alves and Renan Moura and Aldebaro Klautau},
    journal   = {XII Workshop de Software Livre},
    title     = {M\'{o}dulo de Adapta\c{c}\~{a}o de Locutor utilizando Regress\~{a}o Linear de M\'{a}xima Verossimilhan\c{c}a para Sistemas de Reconhecimento de Voz},
    year      = {2010}
}

@article{Siravenha09,
    author    = {Ana Siravenha and Nelson Neto and Valquiria Macedo and Aldebaro Klautau},
    journal   = {Interactive Computer Aided Blended Learning},
    title     = {A Computer-assisted Learning Software Using Speech Synthesis and Recognition in Brazilian Portuguese},
    year      = {2009}
}

@article{Patrick09,
    author    = {Patrick Silva and Nelson Neto and Aldebaro Klautau},
    journal   = {In XXVII Simp\'{o}sio Brasileiro de Telecomunica\c{c}\~{o}es},
    title     = {Novos Recursos e Utiliza\c{c}\~{a}o de Adapta\c{c}\~{a}o de Locutor no Desenvolvimento de um Sistema de Reconhecimento de Voz para o {P}ortugu\^{e}s {B}rasileiro},
    year      = {2009}
}

@article{Trancoso09,
    author    = {Alberto Abad and Isabel Trancoso and Nelson Neto and Maria Ribeiro},
    journal   = {In Interspeech, Brighton, UK},
    title     = {Porting an {E}uropean {P}ortuguese Broadcast News Recognition System to {B}razilian {P}ortuguese},
    year      = {2009}
}

@article{Morais09,
    author    = {Jefferson Morais and Nelson Neto and Aldebaro Klautau},
    journal   = {7th Brazilian Symposium in Information and Human Language
Technology},
    title     = {Tecnologias para o Desenvolvimento de Sistemas de Di\'{a}logo Falado em
{P}ortugu\^{e}s {B}rasileiro},
    year      = {2009}
}

@article{NelsonCALL08,
    author    = {Nelson Neto and Carolina Siravenha and V\'{a}lquiria Macedo and Aldebaro Klautau},
    journal   = {International Conference on Computational Processing of the Portuguese Language - Special Session},
    title     = {A Computer-Assisted Learning Software to Help Teaching English to Brazilians},
    year      = {2008}
}

@article{Patrick08,
    author    = {Patrick Silva and Nelson Neto and Aldebaro Klautau and Andre Adami and Isabel Trancoso},
    journal   = {XXVI Simp\'{o}sio Brasileiro de Telecomunica\c{c}\~{o}es},
    title     = {Speech Recognition for {B}razilian {P}ortuguese using the {S}poltech and {OGI}-22 Corpora},
    year      = {2008}
}

@article{Nelson08,
    author    = {N. Neto and P. Silva and A. Klautau and A. Adami},
    journal   = {International Conference on Computational Processing of Portuguese Language - PROPOR},
    title     = {Spoltech and {OGI}-22 Baseline Systems for Speech Recognition in {B}razilian {P}ortuguese},
    year      = {2008}
}

@article{Siravenha08,
    author    = {Ana Siravenha and Nelson Neto and Valqu\'{i}ria Macedo and Aldebaro Klautau},
    journal   = {7th International Information and Telecommunication Technologies Symposium},
    title     = {Uso de Regras Fonol\'{o}gicas com Determina\c{c}\~{a}o de Vogal T\^{o}nica para Convers\~{a}o Grafema-Fone em {P}ortugu\^{e}s {B}rasileiro},
    year      = {2008}
}

@article{Hosn06a,
    author    = {Chadia Hosn and Luiz Baptista and Tales Imbiriba and Aldebaro Klautau},
    journal   = {In VI International Telecommunications Symposium},
    title     = {New Resources for {B}razilian {P}ortuguese: Results for Grapheme-to-Phoneme and Phone Classification},
    year      = {2006}
}

@inproceedings{Hosn06,
    author    = {C. {Hosn} and L. A. {Baptista} and T. {Imbiriba} and A. {Klautau}},
    booktitle = {2006 International Telecommunications Symposium},
    doi       = {10.1109/ITS.2006.4433322},
    issn      = {},
    keywords  = {hidden Markov models;learning (artificial intelligence);natural languages;speech processing;Brazilian Portuguese;grapheme-to-phoneme conversion;phone classification;speech processing;data-driven technology;baseline BP system;hidden Markov model;machine learning method;Natural languages;Speech processing;Hidden Markov models;Decision trees;Dictionaries;Speaker recognition;Learning systems;Testing;Speech recognition;Classification tree analysis;Grapheme-to-phoneme;letter-to-sound;decision trees;phone classification;hidden Markov models},
    month     = {Sep.},
    number    = {},
    pages     = {477-482},
    title     = {New resources for Brazilian Portuguese: Results for grapheme-to-phoneme and phone classification},
    volume    = {},
    year      = {2006}
}

@article{Neto05,
    author    = {N. Neto and E. Sousa and V. Macedo and A. Adami and A. Klautau},
    journal   = {6th F\'{o}rum Internacional Software Livre},
    title     = {Desenvolvimento de Software Livre Usando Reconhecimento e S\'{i}ntese de Voz: O Estado da Arte para o {P}ortugu\^{e}s {B}rasileiro},
    year      = {2005}
}

@article{Silva05,
    author    = {Enio Silva and Luiz Baptista and Helane Fernandes and Aldebaro Klautau},
    journal   = {XXV Congresso da Sociedade Brasileira de Computa\c{c}\~{a}o},
    title     = {Desenvolvimento de um Sistema de Reconhecimento Autom\'{a}tico de Voz Cont\'{i}nua com Grande Vocabul\'{a}rio para o {P}ortugu\^{e}s {B}rasileiro},
    year      = {2005}
}

@inproceedings{Imbiriba04,
    author    = {T. Imbiriba and A. Klautau and N. Parihar and S. Raghavan and J. Picone},
    booktitle = {Proceedings of the 2004 IEEE International Workshop on Machine Learning for Signal Processing},
    city      = {Sao Luis},
    country   = {Brazil},
    month     = {September},
    pages     = {371-380},
    title     = {{GMM} And Kernel-Based Speaker Recognition with the {ISIP} Toolkit},
    year      = {2004}
}

@inproceedings{Silva04,
    author    = {Enio Silva and Marcus Pantoja and Jackline Celid\^{o}nio and Aldebaro Klautau},
    booktitle = {III Workshop em Tecnologia da Informa\c{c}\~{a}o e da Linguagem Humana},
    city      = {Salvador},
    title     = {Modelos de Linguagem N-grama para Reconhecimento de Voz com Grande Vocabul\'{a}rio},
    year      = {2004}
}

@article{Klautau03-ieee,
    author    = {A. Klautau and N. Jevti\'c and A. Orlitsky},
    journal   = {submitted to IEEE Transactions on Education},
    title     = {A gentle introduction to maximum mutual information estimation},
    year      = {2003}
}

@inproceedings{Klautau03-rbf,
    author    = {A. Klautau},
    booktitle = {SBT, Rio de Janeiro, Brazil},
    title     = {A new algorithm for training {RBF} networks},
    year      = {2003}
}

@inproceedings{Klautau03-icassp,
    author    = {A. Klautau},
    booktitle = {ICASSP},
    title     = {Mining speech: {A}utomatic selection of heterogeneous features using boosting},
    year      = {2003}
}

@article{Klautau03-jmlr,
    author    = {Klautau, A. and Jevti\'c, N. and Orlitsky, A.},
    journal   = {Journal of Machine Learning Research},
    title     = {On nearest-neighbor {ECOC} with application to all-pairs multiclass {SVM}},
    year      = {2003}
}

@inproceedings{Klautau03-sbt,
    author    = {A. Klautau and N. Jevti\'c and A. Orlitsky},
    booktitle = {SBT, Rio de Janeiro, Brazil},
    title     = {Speech recognition based on discriminative classifiers},
    year      = {2003}
}

@techreport{Klautau02d,
    author      = {A. Klautau},
    institution = {UFPA, \emph{http://www.laps.ufpa.br/aldebaro/papers}},
    title       = {Classification of {P}eterson and {B}arney's vowels using {W}eka},
    year        = {2002}
}

@inproceedings{Klautau02,
    author    = {A. Klautau and N. Jevti\'c and A. Orlitsky},
    booktitle = {ICSLP},
    title     = {Combined binary classifiers with applications to speech recognition},
    year      = {2002}
}

@inproceedings{Jevtic01,
    author    = {N. Jevti\'c and A. Klautau and A. Orlitsky},
    booktitle = {Automatic Speech Recognition and Understanding Workshop},
    title     = {Estimated rank pruning and {J}ava-based speech recognition},
    year      = {2001}
}