Computer software for identification of noise source and automatic noise measurement

Fujii, Kenji; Sakurai, Masatsugu; Ando, Yoichi

doi:10.1016/j.jsv.2004.03.019

Cited by 12 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…3). As a first step, the sound signal is framed by employing a rectangular window of 500 ms [following the recommendation of (Fujii et al, 2004)] with 50% of overlap between the windows. Then after applying an A-weighting filter (to model the spectral response of the human outer-middle ear), the windowed signal is passed through a filter bank that splits it into N different narrow band signals.…”

Section: Methodsmentioning

confidence: 99%

“…In environmental acoustics, this technique was used to parameterize acoustic signatures of aircrafts (Fujii et al, 2001), road traffic (Fujii et al, 2002) and railway noises (Sakai et al, 2002), as well as diverse background noises (Yang and Barkana, 2009). In Fujii et al (2004) an automatic noise measurement system based on ACF signal features was proposed. However, this work lacked a complete experimental evaluation.…”

Section: B Previous Work On Acf Signal Analysismentioning

confidence: 99%

See 1 more Smart Citation

Narrow-band autocorrelation function features for the automatic recognition of acoustic environments

Valero

Álías

2013

The Journal of the Acoustical Society of America

View full text Add to dashboard Cite

Acoustic environments are typically composed of multiple sound sources of different typologies, making them especially complex to model and parameterize. To develop an automatic acoustic environment recognition system, this work proposes a spectro-temporal signal parameterization technique inspired by human perception. The proposed parameters are derived from the analysis of the autocorrelation function of narrow-band signals (NB-ACF) obtained from an auditory gammatone filter bank. Five features related to acoustic phenomena are extracted from the NB-ACF to parameterize sound signals. Experiments are conducted on a 4 h sound database (composed of 15 different acoustic environments) employing four different machine learning techniques: K-nearest neighbor, Gaussian mixture models, neural networks and support vector machines. The averaged recognition rates increase by 4.5% when using the proposed NB-ACF features instead of the popular Mel frequency cepstral coefficients. The improvement is even greater (5.6%) when the features are tested in acoustic environments from unknown locations. These results are attributed to the better modeling of the acoustic environments thanks to the complementarity of the spectro-temporal features derived from NB-ACF analysis.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: B Previous Work On Acf Signal Analysismentioning

confidence: 99%

Narrow-band autocorrelation function features for the automatic recognition of acoustic environments

Valero

Álías

2013

The Journal of the Acoustical Society of America

View full text Add to dashboard Cite

show abstract

“…In the previous studies (Ando & Pompoli, 2002;Fujii, Sakurai, & Ando, 2004;Sakai & Ando, 2001), noise sources were identified based on the similarity of acoustical parameters from ACF by using the template-matching algorithm. A fundamental assumption is that noises from the same source have similar acoustical qualities and therefore are mapped into the same cluster in feature-space.…”

Section: Database and Feature Extractionmentioning

confidence: 99%

“…A good design of fuzzy classification model should reach three optimizations (Fujii et al, 2004): (i) the least number of fuzzy rules, (ii) the shortest length of fuzzy rules and (iii) the maximal classification recognition rate relatively. Furthermore, accuracy and interpretability are two important objectives in the design of fuzzy classification system (Ando & Pompoli, 2002).…”

Section: Fuzzy Logic Classifiermentioning

confidence: 99%

Automatic environmental noise source classification model using fuzzy logic

Uzkent

Barkana

Yang

2011

Expert Systems with Applications

View full text Add to dashboard Cite

“…En (Fujii et al 2004) se propone un método que utiliza un ordenador personal al que se conectan dos micrófonos espaciados 20 cm a través de la tarjeta de sonido. Se calculan la función de autocorrelación y la que los autores denominan función de correlación interaural cruzada para determinar el nivel de presión producido por un evento sonoro.…”

Section: Aplicación De Técnicas De Reconocimiento De Patrones…unclassified

Aportaciones a los sistemas de discriminación de fuentes sonoras en la medida de ruido en aeropuertos

Rivera¹

View full text Add to dashboard Cite

La investigación nunca fue mi fin, ni el doctorado mi objetivo, por eso, en este momento en que la meta está tan cerca, mi agradecimiento para Manuel Recuero, por su impulso y apoyo en este recorrido.A lo largo de estos años, y desde que era becario, Mariano y Raúl me han demostrado en infinidad de ocasiones su apoyo, su compañerismo y su amistad. Gracias por escucharme y aguantarme, por orientarme y por ayudarme a poner en valor mis logros sin empujarme hacia la autocomplacencia.Gracias también a ti Nacho, por tu ayuda inestimable desde que se dio la salida en esta carrera de obstáculos. Y a todos los miembros del Grupo de Investigación I2A2, de Labenac y de Lacainac, porque siempre he contado con vuestro apoyo, y porque gracias a vuestra esfuerzo y dedicación, he contado con el suporte del Grupo, sin el que esta tesis hubiera sido imposible.Por suspuesto, el Politecnico di Milano también ocupa un lugar importante en mi lista de agradecimientos. Gracias Giovanni, gracias Marco, porque no olvidaré vuestra colaboración, vuestra ayuda, y vuestra involucración durante mi estancia en Lecco.Así mismo, debo agradecer la colaboración de AENA y SEA Milano, por facilitar el acceso a sus instalaciones, sin el cual la adquisición de material sonoro hubiera quedado seriamente comprometida.También quisiera agradecer a todos los que de forma desinteresada han participado en el ejercicio de intercomparación que ha dotado de contenido a una de las líneas de investigación seguidas en esta tesis..

show abstract

Computer software for identification of noise source and automatic noise measurement

Cited by 12 publications

References 12 publications

Narrow-band autocorrelation function features for the automatic recognition of acoustic environments

Narrow-band autocorrelation function features for the automatic recognition of acoustic environments

Automatic environmental noise source classification model using fuzzy logic

Aportaciones a los sistemas de discriminación de fuentes sonoras en la medida de ruido en aeropuertos

Contact Info

Product

Resources

About