Near-field signal acquisition for smartglasses using two acoustic vector-sensors

Levin, Dovid Y.; Habets, Emanuël A. P.; Gannot, Sharon

doi:10.1016/j.specom.2016.07.002

Cited by 11 publications

(6 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There have been several wearable array designs reported in the literature, including helmets [8][9][10], eyeglasses [11,12], and vests [13,14]. However, these designs have been restricted to small areas of the body and the literature offers little guidance about how microphone placement affects performance.…”

Section: Introductionmentioning

confidence: 99%

Acoustic Impulse Responses for Wearable Audio Devices

Corey

Tsuda

Singer

2019

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

We present an open-access dataset of over 8000 acoustic impulse from 160 microphones spread across the body and affixed to wearable accessories. The data can be used to evaluate audio capture and array processing systems using wearable devices such as hearing aids, headphones, eyeglasses, jewelry, and clothing. We analyze the acoustic transfer functions of different parts of the body, measure the effects of clothing worn over microphones, compare measurements from a live human subject to those from a mannequin, and simulate the noise-reduction performance of several beamformers. The results suggest that arrays of microphones spread across the body are more effective than those confined to a single device.

show abstract

Section: Introductionmentioning

confidence: 99%

Acoustic Impulse Responses for Wearable Audio Devices

Corey

Tsuda

Singer

2019

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

show abstract

“…Hearing aid [15,16] Helmet [17] Smart glasses [18] Hat [25] Proposed Specifically, Wearable SELD dataset consists of the following. Earphone type dataset: This dataset contains data collected by 12 microphones placed around ears.…”

Section: Seldnetmentioning

confidence: 99%

“…However, due to the predetermined array geometry, it restricts the variation of microphone arrangement required in a specific application. Therefore, several other configurations have been considered in SEL to extend the range of applications [15][16][17][18][19]. Some datasets using wearable deivces are publicly available, but these are not suitable for SELD task because of the number of impulse responses (IRs) recordings.…”

Section: Introductionmentioning

confidence: 99%

Wearable SELD dataset: Dataset for sound event localization and detection using wearable devices around head

Nagatomo¹,

Yasuda²,

Yatabe³

et al. 2022

Preprint

View full text Add to dashboard Cite

Sound event localization and detection (SELD) is a combined task of identifying the sound event and its direction. Deep neural networks (DNNs) are utilized to associate them with the sound signals observed by a microphone array. Although ambisonic microphones are popular in the literature of SELD, they might limits the range of applications due to their predetermined geometry. Some applications (including those for pedestrians that perform SELD while walking) require a wearable microphone array whose geometry can be designed to suit the task. In this paper, for development of such a wearable SELD, we propose a dataset named Wearable SELD dataset. It consists of data recorded by 24 microphones placed on a head and torso simulators (HATS) with some accessories mimicking wearable devices (glasses, earphones, and headphones). We also provide experimental results of SELD using the proposed dataset and SELDNet to investigate the effect of microphone configuration.Index Terms-Sound event localization (SEL), direction of arrival (DOA), sound event detection (SED), deep neural network (DNN), head and torso simulator (HATS).

show abstract

“…Amazon Echo or Google Home) the majority of available Cocktail Party scenario datasets focus on recordings from distant microphone arrays 8 – 17 . Compared to the rapidly increasing number of hearing aid and implant users worldwide 18 , acoustic Cocktail Party datasets with microphones located at the human head are scarce and limited with respect to the number of human participants 19 – 23 , the number or placement of microphones 9 , 10 , 20 – 25 or the acoustic stimuli that do not cover varying signal-to-noise ratios (SNRs) or Cocktail Party scenarios 19 , 24 , 26 , 27 . In addition, many available datasets lack specifications of the microphones’ positions and the spatial arrangement of the individual sound sources, which makes it difficult to characterize the occurring interaural or inter-microphone time and level differences 28 , 29 .…”

Section: Background and Summarymentioning

confidence: 99%

Multichannel acoustic source and image dataset for the cocktail party effect in hearing aid and implant users

2020

View full text Add to dashboard Cite

The Cocktail Party Effect refers to the ability of the human sense of hearing to extract a specific target sound source from a mixture of background noises in complex acoustic scenarios. The ease with which normal hearing people perform this challenging task is in stark contrast to the difficulties that hearing-impaired subjects face in these situations. To help patients with hearing aids and implants, scientists are trying to imitate this ability of human hearing, with modest success so far. To support the scientific community in its efforts, we provide the Bern Cocktail Party (BCP) dataset consisting of 55938 Cocktail Party scenarios recorded from 20 people and a head and torso simulator wearing cochlear implant audio processors. The data were collected in an acoustic chamber with 16 synchronized microphones placed at purposeful positions on the participants’ heads. In addition to the multi-channel audio source and image recordings, the spatial coordinates of the microphone positions were digitized for each participant. Python scripts were provided to facilitate data processing.

show abstract

Near-field signal acquisition for smartglasses using two acoustic vector-sensors

Cited by 11 publications

References 23 publications

Acoustic Impulse Responses for Wearable Audio Devices

Acoustic Impulse Responses for Wearable Audio Devices

Wearable SELD dataset: Dataset for sound event localization and detection using wearable devices around head

Multichannel acoustic source and image dataset for the cocktail party effect in hearing aid and implant users

Contact Info

Product

Resources

About