Filters








15,445 Hits in 6.1 sec

Environmental Sound Recognition Using Time-Frequency Intersection Patterns

Xuan Guo, Yoshiyuki Toyoda, Huankang Li, Jie Huang, Shuxue Ding, Yong Liu
2012 Applied Computational Intelligence and Soft Computing  
Spectra of many environmental sounds change more slowly than those of speech or voice, so the intersectional time-frequency pattern will preserve the major features of environmental sounds but with drastically  ...  The input data is a combination of time-variance pattern of instantaneous powers and frequency-variance pattern with instantaneous spectrum at the power peak, referred to as a time-frequency intersection  ...  We call this input data type a time frequency intersection pattern and refer to the timevariance patter of power as power-variance pattern.  ... 
doi:10.1155/2012/650818 fatcat:hfbnqvmtxfhidkilf35ymd5wzm

A Proposed Method for the Sound Recognition Process

2018 Engineering and Technology Journal  
Sounds can be recognized under suitable recording conditions by converting the sound signal from time to frequency domain (because Sound signal of a source differs from other sources by the frequency contents  ...  The main problem faces the recognition process is the 100% system accuracy cannot be achieved. A proposed strategy suggested solvi ng the problem.  ...  [3] designed a system for environmental sound recognition using time-frequency intersection patterns with a recognition rate for about 92%.  ... 
doi:10.30684/etj.36.8a.15 fatcat:5fx4w2yhfjervirgoujzd7aj6a

Acoustic feature extraction by statistics based local binary pattern for environmental sound classification

Takumi Kobayashi, Jiaxing Ye
2014 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
The proposed method is motivated from the image processing technique, local binary pattern (LBP), and works on a spectrogram which forms two-dimensional (time-frequency) data like an image.  ...  In the experiments on environmental sound classification using RWCP dataset that contains 105 sound categories, the proposed method produces the superior performance (98.62%) compared to the other methods  ...  [6] extract the time-frequency intersection patterns from the spectrogram similarly to image projection profile. Dennis et al. [4] establish the moment-based spectrogram features.  ... 
doi:10.1109/icassp.2014.6854161 dblp:conf/icassp/KobayashiY14 fatcat:bhyxas4vgzg6bdaiopnsn4elfy

Awareness Science and Engineering

Qiangfu Zhao, Cheng-Hsiung Hsieh, Keitaro Naruse, Zhishun She
2012 Applied Computational Intelligence and Soft Computing  
Guo et al. entitled "Environmental sound recognition using time-frequency intersection patterns,"  ...  Guo et al. entitled "Environmental sound recognition using time-frequency intersection patterns"). In this issue we put more weight on the scientific aspect of AC, rather than simple applications.  ...  In this paper, a two-stage method for environmental sound recognition using neural networks (NNs) is proposed. It includes a classification stage and a recognition stage.  ... 
doi:10.1155/2012/182849 fatcat:i6a5u6pxdvcj3kf4f2e35tsyjy

Wind Sounds Classification Using Different Audio Feature Extraction Techniques

Wala'a Nsaif Jasim, Saba Abdual Wahid Saddam, Esra'a Jasem Harfash
2022 Informatica (Ljubljana, Tiskana izd.)  
The CNN classification method is implemented to determine the class of input wind sound signal.  ...  Experimental results show that each of these extraction feature methods give different results, but classification accuracy that are obtained by using PLP features return the best results.  ...  By their experiment, Mel-frequency cepstral coefficient (MFCC) features were extracted from the audio. MFCC features are wide used in environmental sound recognition and in speech recognition.  ... 
doi:10.31449/inf.v45i7.3739 fatcat:di3qc3tltnejzfdodlribmj4cq

Neural Population Coding for Effective Temporal Classification [article]

Zihan Pan, Jibin Wu, Yansong Chua, Malu Zhang, Haizhou Li
2019 arXiv   pre-print
Neural encoding plays an important role in faithfully describing the temporally rich patterns, whose instances include human speech and environmental sounds.  ...  We show that, with population neural codings, the encoded patterns are linearly separable using the Support Vector Machine (SVM).  ...  The SNN models have been successfully applied for many pattern recognition tasks, instances include image classification [11] , automatic speech recognition (ASR) [12] - [15] and environmental sound  ... 
arXiv:1909.08018v2 fatcat:n4ie5qoolbd3pfprba5ba4sgcy

Acoustic Hazard Detection for Pedestrians With Obscured Hearing

Justin Lee, Andry Rakotonirainy
2011 IEEE transactions on intelligent transportation systems (Print)  
Index Terms-Environmental Sound Recognition, Pedestrian Safety I.  ...  BACKGROUND A typical approach to environmental sound recognition involves feature extraction with a time-frequency algorithm, such as wavelets or a Short Time Fourier Transform (STFT), followed by classification  ... 
doi:10.1109/tits.2010.2100383 fatcat:26botthodffppjgcfv4leytozu

Acoustic Hazard Detection for Pedestrians With Obscured Hearing

Justin Lee, Andry Rakotonirainy
2011 IEEE transactions on intelligent transportation systems (Print)  
Index Terms-Environmental Sound Recognition, Pedestrian Safety I.  ...  BACKGROUND A typical approach to environmental sound recognition involves feature extraction with a time-frequency algorithm, such as wavelets or a Short Time Fourier Transform (STFT), followed by classification  ... 
doi:10.1109/tits.2011.2163154 fatcat:pzw5rb66enci5ggdl3r7f6tlxa

The Verification of Voice Recognition Using Cmusphinx and DTW

Gusti Made Arya Sasmita, I Putu Arya Dharmaadi, Henrico Aldy Ferdian
2020 International Journal of Computer Applications Technology and Research  
MFCC (Mel Frequency Cepstrum Coefficients) is as a characteristic extraction method on a digital sound signal. Matching process with saved data uses DTW (Dynamic Time Warping) method.  ...  The use of smartphones to maintain data security is still low, which generally only uses conventional method as security systems available on smartphone devices, such as word combinations, PINs or patterns  ...  This study focuses on developing a system for speech recognition using dynamic time warping (DTW) algorithms by comparing sound speaker signals with sound signals already stored in the database, and extracting  ... 
doi:10.7753/ijcatr0902.1007 fatcat:bvdpxmlewzgpbe2gmhnelf5il4

A Survey on Human Behavior Recognition Using Smartphone-based Ultrasonic Signal

Zhengjie Wang, Yushan Hou, Kangkang Jiang, Chengming Zhang, Wenwen Dou, Zehua Huang, Yinjing Guo
2019 IEEE Access  
In this paper, we first review the common behavior recognition techniques including light, video, sound, and frequency radio and outline their main characteristics.  ...  shift, and time of flight (ToF) to recognize human behavior.  ...  It captures the sound signals reflected by moving a finger on the table surface, extracts time and frequency features, and identifies stroke using pattern classification approaches.  ... 
doi:10.1109/access.2019.2931088 fatcat:ajuq6a4cr5coxjxfompyd5xnpe

Robust Audio Localization for Mobile Robots in Industrial Environments [chapter]

Manuel Manzanares, Yolanda Bolea, Antoni Grau
2011 Advances in Sound Localization  
Experiments and discussions Method based on the recognition of patterns of the audio signal In the first proposed method based on the recognition of patterns of the audio signal, in order to prepare  ...  Method based on the recognition of patterns of the audio signal This method is based on the recognition of patterns in the acquired audio signal by the robot in different locations, to establish the signals  ...  The wide spectrum of sound frequencies that range from infrasounds through acoustic sounds to ultrasounds, also introduces difficulties, as different spectrum components have different penetration properties  ... 
doi:10.5772/14517 fatcat:wgpioio3anbczcsm5zbk4q3vhe

Analysis of Waveform Spectrum of Compact Fan Motor Applying MT System

Eiji Toma
2018 Journal of the Institute of Industrial Applications Engineers  
The demand for compact fan motor increases for cooling use in the electronic equipment by weight saving of IT apparatus, spacing-saving now.  ...  Development of a measuring device for quantitatively examine the sound and vibration level and quality of a small fan motor is required in order to improve the problems in these inspection processes.  ...  In the case of using pattern recognition method, processing for extracting feature value from measurement data is performed.  ... 
doi:10.12792/jiiae.6.1 fatcat:poj4sm64pvfejdabn6vvuspdrq

Frequency-Limiting Effects on Speech and Environmental Sound Identification for Cochlear Implant and Normal Hearing Listeners

Son-A Chang, Jong Ho Won, HyangHee Kim, Seung-Ha Oh, Richard S. Tyler, Chang Hyun Cho
2018 Journal of Audiology and Otology  
Speech and environmental sound recognition by individuals with CI and normal-hearing (NH) was measured.  ...  J Audiol Otol 2018;22(1):28-38 KEY WORDS:0 Frequency information · Cross-over frequency · Korean speech sound · Environmental sound · Cochlear implant.  ...  The significant relationship between speech and non-speech environmental sound identification shown in Fig. 4 suggests that speech and environmental sounds may share similar pattern of perception and  ... 
doi:10.7874/jao.2017.00178 pmid:29325391 pmcid:PMC5784366 fatcat:axy6qql4kzg6da6ieqepwp5rfu

Localize Animal Sound Events Reliably (LASER): A New Software for Sound Localization in Zoos

Sebastian Schneider, Paul Wilhelm Dierkes
2021 Journal of Zoological and Botanical Gardens  
In addition, tests were carried out under real conditions using the example of the giant otter enclosure at Dortmund Zoo, Germany.  ...  Locating a vocalizing animal can be useful in many fields of bioacoustics and behavioral research, and is often done in the wild, covering large areas.  ...  Applying the Software LASER to Zoo Conditions and Limitations In this study, video recordings were used for evaluation to verify sound localization and individual recognition via the software LASER.  ... 
doi:10.3390/jzbg2020011 fatcat:2rj747mtuzfrtphwbtxhgjipv4

Deep Networks tag the location of bird vocalisations on audio spectrograms [article]

Lefteris Fanioudakis, Ilyas Potamitis
2017 arXiv   pre-print
Acoustic detection of avian sounds can be used for the automatized monitoring of multiple bird taxa and querying in long-term recordings for species of interest.  ...  We focus solely on procedures requiring minimum human attendance, suitable to scan massive volumes of data, in order to analyze them, evaluate insights and hypotheses and identify patterns of bird activity  ...  For all DenseNets implementations we used the Keras 2 framework on top of the TensorFlow backend.  ... 
arXiv:1711.04347v1 fatcat:37kcm57prjb75cu3rw6in3py5m
« Previous Showing results 1 — 15 out of 15,445 results