Daniel Nicolalde - Academia.edu (original) (raw)

Uploads

Papers by Daniel Nicolalde

Research paper thumbnail of Autenticação de áudio digital com base na mudança de fase da frequência da rede elétrica

Resumo-Este artigo propõe um método para autenticação de áudio, que consiste em verificar se um s... more Resumo-Este artigo propõe um método para autenticação de áudio, que consiste em verificar se um sinal de áudio gravado digitalmente foi ou não adulterado. O método baseia-se na verificação da mudança de fase associada à frequência da rede elétrica, quase sempre embutida nas gravações. Ele fornece uma ferramenta visual que permite localizar as mudanças abruptas de fase da frequência da rede indicativas de pontos de edição, e uma medida característica que permite discriminar automaticamente, por uma razão de verossimilhança, sinais originais de editados. Apresentam-se os fundamentos teóricos e questões práticas de implementação da técnica, aferindo-se seu desempenho sobre uma base de sinais reais digitalmente editados. Palavras-Chave-Autenticação de áudio digital, frequência da rede elétrica, mudança abrupta de fase da frequência da rede.

Research paper thumbnail of Audio Authenticity Based On The Discontinuity Of Enf Higher Harmonics

Publication in the conference proceedings of EUSIPCO, Marrakech, Morocco, 2013

Research paper thumbnail of Presence-absence estimation in audio recordings of tropical frog communities

ArXiv, 2019

One non-invasive way to study frog communities is by analyzing long-term samples of acoustic mate... more One non-invasive way to study frog communities is by analyzing long-term samples of acoustic material containing calls. This immense task has been optimized by the development of Machine Learning tools to extract ecological information. We explored a likelihood-ratio audio detector based on Gaussian mixture model classification of 10 frog species, and applied it to estimate presence-absence in audio recordings from an actual amphibian monitoring performed at Yasuni National Park in the Ecuadorian Amazonia. A modified filter-bank was used to extract 20 cepstral features that model the spectral content of frog calls. Experiments were carried out to investigate the hyperparameters and the minimum frog-call time needed to train an accurate GMM classifier. With 64 Gaussians and 12 seconds of training time, the classifier achieved an average weighted error rate of 0.9% on the 10-fold cross-validation for nine species classification, as compared to 3% with MFCC and 1.8% with PLP features. ...

Research paper thumbnail of Labeled frog-call dataset of Yasuní National Park for training Machine Learning algorithms

Research paper thumbnail of Selección, anotación y etiquetado de los cantos de las ranas del Ecuador

revistapuce

El presente trabajo explica el estándar y prácticas de selección, anotación y etiquetado del mate... more El presente trabajo explica el estándar y prácticas de selección, anotación y etiquetado del material bioacústico para grabaciones que contengan cantos de ranas. El objetivo es disponer de una base de datos de señales acústicas de cantos de ranas presentes en el Parque Nacional Yasuní en Ecuador considerando que los cantos anotados son una valiosa fuente de información para investigación de reconocimiento automático de especies. Este documento explica el procedimiento de selección de audio en buen estado, así como el procedimiento de anotación. En la selección de audio se evitarán sonidos con baja relación-señala-ruido, con presencia de voz humana, con ruidos mecánicos y señales saturadas.En el procedimiento de anotación, se usan etiquetas estándar para marcar el intervalo de anotación, los cantos de rana por especie y cada nota. Esta base de datos servirá como referencia para desarrollo de aplicaciones bioacústicas, bioinformáticas y de procesamiento digital de señales en tareas qu...

Research paper thumbnail of Evaluating digital audio authenticity with spectral distances and ENF phase change

2009 IEEE International Conference on Acoustics, Speech and Signal Processing, 2009

This paper discusses the use of spectral distances obtained from adaptive filters employed as lin... more This paper discusses the use of spectral distances obtained from adaptive filters employed as linear predictors and phase change of the electric network frequency to evaluate digital audio authenticity. An authenticity evaluation may be of paramount importance for audio forensics and may help a criminalistic laboratory when dealing with audio evidence in a court of law. We present in this paper a theoretical background of the proposed scheme and show results with digitally edited speech.

Research paper thumbnail of Evaluating digital audio authenticity with spectral distances and ENF phase change

2009 IEEE International Conference on Acoustics, Speech and Signal Processing, 2009

This paper discusses the use of spectral distances obtained from adaptive filters employed as lin... more This paper discusses the use of spectral distances obtained from adaptive filters employed as linear predictors and phase change of the electric network frequency to evaluate digital audio authenticity. An authenticity evaluation may be of paramount importance for audio forensics and may help a criminalistic laboratory when dealing with audio evidence in a court of law. We present in this paper a theoretical background of the proposed scheme and show results with digitally edited speech.

Research paper thumbnail of Evaluating digital audio authenticity with spectral distances and ENF phase change

2009 IEEE International Conference on Acoustics, Speech and Signal Processing, 2009

This paper discusses the use of spectral distances obtained from adaptive filters employed as lin... more This paper discusses the use of spectral distances obtained from adaptive filters employed as linear predictors and phase change of the electric network frequency to evaluate digital audio authenticity. An authenticity evaluation may be of paramount importance for audio forensics and may help a criminalistic laboratory when dealing with audio evidence in a court of law. We present in this paper a theoretical background of the proposed scheme and show results with digitally edited speech.

Research paper thumbnail of Autenticação de áudio digital com base na mudança de fase da frequência da rede elétrica

Resumo-Este artigo propõe um método para autenticação de áudio, que consiste em verificar se um s... more Resumo-Este artigo propõe um método para autenticação de áudio, que consiste em verificar se um sinal de áudio gravado digitalmente foi ou não adulterado. O método baseia-se na verificação da mudança de fase associada à frequência da rede elétrica, quase sempre embutida nas gravações. Ele fornece uma ferramenta visual que permite localizar as mudanças abruptas de fase da frequência da rede indicativas de pontos de edição, e uma medida característica que permite discriminar automaticamente, por uma razão de verossimilhança, sinais originais de editados. Apresentam-se os fundamentos teóricos e questões práticas de implementação da técnica, aferindo-se seu desempenho sobre uma base de sinais reais digitalmente editados. Palavras-Chave-Autenticação de áudio digital, frequência da rede elétrica, mudança abrupta de fase da frequência da rede.

Research paper thumbnail of Audio Authenticity Based On The Discontinuity Of Enf Higher Harmonics

Publication in the conference proceedings of EUSIPCO, Marrakech, Morocco, 2013

Research paper thumbnail of Presence-absence estimation in audio recordings of tropical frog communities

ArXiv, 2019

One non-invasive way to study frog communities is by analyzing long-term samples of acoustic mate... more One non-invasive way to study frog communities is by analyzing long-term samples of acoustic material containing calls. This immense task has been optimized by the development of Machine Learning tools to extract ecological information. We explored a likelihood-ratio audio detector based on Gaussian mixture model classification of 10 frog species, and applied it to estimate presence-absence in audio recordings from an actual amphibian monitoring performed at Yasuni National Park in the Ecuadorian Amazonia. A modified filter-bank was used to extract 20 cepstral features that model the spectral content of frog calls. Experiments were carried out to investigate the hyperparameters and the minimum frog-call time needed to train an accurate GMM classifier. With 64 Gaussians and 12 seconds of training time, the classifier achieved an average weighted error rate of 0.9% on the 10-fold cross-validation for nine species classification, as compared to 3% with MFCC and 1.8% with PLP features. ...

Research paper thumbnail of Labeled frog-call dataset of Yasuní National Park for training Machine Learning algorithms

Research paper thumbnail of Selección, anotación y etiquetado de los cantos de las ranas del Ecuador

revistapuce

El presente trabajo explica el estándar y prácticas de selección, anotación y etiquetado del mate... more El presente trabajo explica el estándar y prácticas de selección, anotación y etiquetado del material bioacústico para grabaciones que contengan cantos de ranas. El objetivo es disponer de una base de datos de señales acústicas de cantos de ranas presentes en el Parque Nacional Yasuní en Ecuador considerando que los cantos anotados son una valiosa fuente de información para investigación de reconocimiento automático de especies. Este documento explica el procedimiento de selección de audio en buen estado, así como el procedimiento de anotación. En la selección de audio se evitarán sonidos con baja relación-señala-ruido, con presencia de voz humana, con ruidos mecánicos y señales saturadas.En el procedimiento de anotación, se usan etiquetas estándar para marcar el intervalo de anotación, los cantos de rana por especie y cada nota. Esta base de datos servirá como referencia para desarrollo de aplicaciones bioacústicas, bioinformáticas y de procesamiento digital de señales en tareas qu...

Research paper thumbnail of Evaluating digital audio authenticity with spectral distances and ENF phase change

2009 IEEE International Conference on Acoustics, Speech and Signal Processing, 2009

This paper discusses the use of spectral distances obtained from adaptive filters employed as lin... more This paper discusses the use of spectral distances obtained from adaptive filters employed as linear predictors and phase change of the electric network frequency to evaluate digital audio authenticity. An authenticity evaluation may be of paramount importance for audio forensics and may help a criminalistic laboratory when dealing with audio evidence in a court of law. We present in this paper a theoretical background of the proposed scheme and show results with digitally edited speech.

Research paper thumbnail of Evaluating digital audio authenticity with spectral distances and ENF phase change

2009 IEEE International Conference on Acoustics, Speech and Signal Processing, 2009

This paper discusses the use of spectral distances obtained from adaptive filters employed as lin... more This paper discusses the use of spectral distances obtained from adaptive filters employed as linear predictors and phase change of the electric network frequency to evaluate digital audio authenticity. An authenticity evaluation may be of paramount importance for audio forensics and may help a criminalistic laboratory when dealing with audio evidence in a court of law. We present in this paper a theoretical background of the proposed scheme and show results with digitally edited speech.

Research paper thumbnail of Evaluating digital audio authenticity with spectral distances and ENF phase change

2009 IEEE International Conference on Acoustics, Speech and Signal Processing, 2009

This paper discusses the use of spectral distances obtained from adaptive filters employed as lin... more This paper discusses the use of spectral distances obtained from adaptive filters employed as linear predictors and phase change of the electric network frequency to evaluate digital audio authenticity. An authenticity evaluation may be of paramount importance for audio forensics and may help a criminalistic laboratory when dealing with audio evidence in a court of law. We present in this paper a theoretical background of the proposed scheme and show results with digitally edited speech.