A comparative study between MFCC and LSF coefficients in automatic recognition of isolated digits pronounced in Portuguese and English

Autor(es)

Silva, Diego Furtado ^[1] ; Alves de Souza, Vinicius Mourao ^[1] ; Prado Alves Batista, Gustavo Enrique de Almeida ^[1]

Afiliação do(s) autor(es)

^[1] Univ Sao Paulo, Inst Ciencias Matemat & Computacao, BR-13566590 Sao Paulo - Brazil

• Tipo de documento: Artigo Científico
• Fonte: ACTA SCIENTIARUM-TECHNOLOGY; v. 35, n. 4, p. 621-628, 2013.
• Citações Web of Science: 2

Resumo

Recognition of isolated spoken digits is the core procedure for a large number of applications which rely solely on speech for data exchange, as in telephone-based services, such as dialing, airline reservation, bank transaction and price quotation. Spoken digit recognition is generally a challenging task since the signals last for a short period of time and often some digits are acoustically very similar to other digits. The objective of this paper is to investigate the use of machine learning algorithms for spoken digit recognition and disclose the free availability of a database with digits pronounced in English and Portuguese to the scientific community. Since machine learning algorithms are fully dependent on predictive attributes to build precise classifiers, we believe that the most important task for successfully recognizing spoken digits is feature extraction. In this work, we show that Line Spectral Frequencies (LSF) provide a set of highly predictive coefficients. We evaluated our classifiers in different settings by altering the sampling rate to simulate low quality channels and varying the number of coefficients. (AU)

• Processo FAPESP: 11/04054-2 - Classificação de séries temporais por similaridade e extração de atributos intrínsecos com aplicação na identificação de espécie de insetos
• Beneficiário: Diego Furtado Silva
• Modalidade de apoio: Bolsas no Brasil - Mestrado
• Processo FAPESP: 12/07295-3 - Invariância à complexidade em classificação, agrupamento e descoberta de motifs em séries temporais
• Beneficiário: Gustavo Enrique de Almeida Prado Alves Batista
• Modalidade de apoio: Auxílio à Pesquisa - Regular
• Processo FAPESP: 11/17698-5 - Classificação de fluxo de dados não estacionários com aplicação em sensores identificadores de insetos
• Beneficiário: Vinícius Mourão Alves de Souza
• Modalidade de apoio: Bolsas no Brasil - Doutorado
• Processo FAPESP: 12/50714-7 - Sensores inteligentes para controle de pragas agrícolas e insetos vetores de doenças
• Beneficiário: Gustavo Enrique de Almeida Prado Alves Batista
• Modalidade de apoio: Auxílio à Pesquisa - Regular