Acoustic environment identification by Kullback–Leibler divergence

Delgado-Gutiérrez, Guillermo; Rodríguez-Santos, Francisco; Jiménez-Ramírez, Omar; Vázquez-Medina, Rubén

doi:10.1016/j.forsciint.2017.10.031

Cited by 3 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In table 3 we summarize the literature which was used. Touchscreen identity (keystroke dynamics [9,12,10,13,11,14,15]) Type E Microphone identity (speaker recognition [16,17,18]), activity [19,20,21], keylogger (for physical keyboard [22,23,24]), location features (AEI [25,26,27,28], room characteristics [29,30,31])…”

Section: Discussionmentioning

confidence: 99%

“…Acoustic environment identification (AEI), as it is commonly known, is mostly limited to room or enclosed space environments where the geometry of the room can have noticeable effects on the reverberation of the audio. The main applications of AEI are in audio forensics where an estimation of the reverberation and background noise from a recording can be used to identify the room or even the location inside a room where the audio was recorded [25,26,27,28]. Prior measurements or estimates of the impulse response of the rooms are required for these methods since they describe how the sound reverberates in that room.…”

Section: Microphonementioning

confidence: 99%

See 1 more Smart Citation

A report on personally identifiable sensor data from smartphone devices

Fanourakis

2020

Preprint

View full text Add to dashboard Cite

An average smartphone is equipped with an abundance of sensors to provide a variety of vital functionalities and conveniences. The data from these sensors can be collected in order to find trends or discover interesting correlations in the data but can also be used by nefarious entities for the purpose of revealing the identity of the persons who generated this data. In this paper, we seek to identify what types of sensor data can be collected on a smartphone and which of those types can pose a threat to user privacy by looking into the hardware capabilities of modern smartphone devices and how smartphone data is used in the literature. We then summarize some implications that this information could have on the GDPR.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Microphonementioning

confidence: 99%

A report on personally identifiable sensor data from smartphone devices

Fanourakis

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Conversation can be defined as interactive communication between individuals. Recording a conversation will clarify the chronology of an event [5].…”

Section: Introductionmentioning

confidence: 99%

“…Noisy environment, wiretapping recording is noise, the audio recording quality is low [7]. This affects the accuracy of the information contained in the recording [5], [8]. Information on a audio record includes individual  ISSN: 2502-4752 Indonesian J Elec Eng & Comp Sci, Vol.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Feature extraction with mel scale separation method on noise audio recordings

Huizen

Kurniati

2021

IJEECS

View full text Add to dashboard Cite

This paper focuses on improving the accuracy of noise audio recordings. High-quality audio recording, extraction using the mel frequency cepstral coefficients (MFCC) method produces high accuracy. While the low-quality is because of noise, the accuracy is low. Improved accuracy by investigating the effect of bandwidth on the mel scale. The proposed improvement uses the mel scale separation methods into two frequency channels (MFCC dual-channel). For the comparison method using the mel scale bandwidth without separation (MFCC single-channel). Feature analysis using k-mean clustering. The data uses a noise variance of up to -16 dB. Testing on the MFCC single-channel method for -16 dB noise has an accuracy of 47.5%, while the MFCC dual-channel method has an accuracy better of 76.25%. The next test used adaptive noise-canceling (ANC) to reduce noise before extraction. The result is that the MFCC single-channel method has an accuracy of 82.5% and the MFCC dual-channel method has an accuracy better of 83.75%. High-quality audio recording testing for the MFCC single-channel method has an accuracy of 92.5% and the MFCC dual-channel method has an accuracy better of 97.5%. The test results show the effect of mel scale bandwidth to increase accuracy. The MFCC dual-channel method has higher accuracy.

show abstract