Title:
NOISE AND ECHO SIGNAL INTEGRATED CANCELLATION DEVICE USING DEEP NEURAL NETWORK HAVING PARALLEL STRUCTURE
Document Type and Number:
WIPO Patent Application WO/2022/158913
Kind Code:
A1
Abstract:
A multi-channel-based noise and echo signal integrated cancellation device using a deep neural network according to an embodiment may comprise: multiple microphone encoders for receiving multiple microphone input signals including an echo signal, a noise signal, and a voice signal of a speaker, converting the multiple microphone input signals into multiple pieces of conversion information, respectively, and outputting the converted information; a channel conversion unit for compressing the multiple pieces of conversion information, converting the compressed information into first input information having a single channel size, and outputting the converted information; a far-end signal encoder for receiving a far-end signal, converting the far-end signal into second input information, and outputting the converted information; an attention unit for outputting weight information by applying an attention mechanism to the first input information and the second input information; a pre-trained first artificial neural network in which third input information corresponding to information obtained by combining the weight information and the second input information is input information, and first output information including mask information for estimating the voice signal from the second input information is output information; and a voice signal estimation unit for outputting an estimated voice signal obtained by estimating the voice signal on the basis of the first output information and the second input information.
Inventors:
CHANG JOON HYUK (KR)
PARK SONG KYU (KR)
PARK SONG KYU (KR)
Application Number:
PCT/KR2022/001165
Publication Date:
July 28, 2022
Filing Date:
January 21, 2022
Export Citation:
Assignee:
IUCF HYU (KR)
International Classes:
G10L21/0208; G06N3/08; G10K11/175; G10L25/30
Foreign References:
| KR20200115107A | 2020-10-07 | |||
| KR20120005920A | 2012-01-17 | |||
| US20180040333A1 | 2018-02-08 | |||
| KR102316626B1 | 2021-10-22 |
Other References:
SEO HYEJI, LEE MOA, CHANG JOON-HYUK: "Integrated acoustic echo and background noise suppression based on stacked deep neural networks", APPLIED ACOUSTICS, vol. 133, 1 April 2018 (2018-04-01), GB , pages 194 - 201, XP055952259, ISSN: 0003-682X, DOI: 10.1016/j.apacoust.2017.12.031
HONGSHENG CHEN; TENG XIANG; KAI CHEN; JING LU: "Nonlinear Residual Echo Suppression Based on Multi-stream Conv-TasNet", ARXIV.ORG, 15 May 2020 (2020-05-15), pages 1 - 5, XP081674382
BARMPOUTIS PANAGIOTIS, PAPAIOANNOU PERIKLIS, DIMITROPOULOS KOSMAS, GRAMMALIDIS NIKOS: "A Review on Early Forest Fire Detection Systems Using Optical Remote Sensing", SENSORS, vol. 20, no. 22, 11 November 2020 (2020-11-11), CH , pages 1 - 26, XP055946762, ISSN: 1424-8220, DOI: 10.3390/s20226442
HONGSHENG CHEN; TENG XIANG; KAI CHEN; JING LU: "Nonlinear Residual Echo Suppression Based on Multi-stream Conv-TasNet", ARXIV.ORG, 15 May 2020 (2020-05-15), pages 1 - 5, XP081674382
BARMPOUTIS PANAGIOTIS, PAPAIOANNOU PERIKLIS, DIMITROPOULOS KOSMAS, GRAMMALIDIS NIKOS: "A Review on Early Forest Fire Detection Systems Using Optical Remote Sensing", SENSORS, vol. 20, no. 22, 11 November 2020 (2020-11-11), CH , pages 1 - 26, XP055946762, ISSN: 1424-8220, DOI: 10.3390/s20226442
Attorney, Agent or Firm:
HAEUM PATENT & LAW FIRM (KR)
Download PDF: