@article {Mizumachi:2021:0736-2935:4355,
title = "Non-linear beamformer with long short-term memory network",
journal = "INTER-NOISE and NOISE-CON Congress and Conference Proceedings",
parent_itemid = "infobike://ince/incecp",
publishercode ="ince",
year = "2021",
volume = "263",
number = "2",
publication date ="2021-08-01T00:00:00",
pages = "4355-4360",
itemtype = "ARTICLE",
issn = "0736-2935",
url = "https://ince.publisher.ingentaconnect.com/content/ince/incecp/2021/00000263/00000002/art00045",
doi = "doi:10.3397/IN-2021-2673",
author = "Mizumachi, Mitsunori and Oka, Ryotarou",
abstract = "Acoustic beamforming with a microphone array enables spatial filtering in a wide frequency range. It is a challenging issue to sharpen the main-lobe in the lower frequency region with a small-scale microphone array, of which the number and spacing of microphones are small. A neural
network-based non-linear beamformer achieves a breakthrough in sharpening the main-lobe. The non-linear beamforming works well for the narrowband signals but is weak in wideband beamforming. The non-linear beamforming with the long short-term memory is proposed to deal with wideband speech
signals. The long short-term memory network is trained in the recurrent neural network architecture with the sequence of audio data such as speech signals. The performance of the proposed beamformer is confirmed using a small-scale 8-ch MEMS microphone array, where eight microphones are linearly
arranged with the neighboring spacing of 10 mm, under a real environment. The beam-pattern of the proposed non-linear beamformer succeeds in sharpening the main-lobe although the linear delay-and-sum beamformer could not achieve frequency selectivity. The feasibility of the proposed beamformer
is also confirmed in speech enhancement.",
}