WO2014104815A1 - 바람 소음 제거를 통한 음원 위치 추적 장치 및 그 방법 - Google Patents
바람 소음 제거를 통한 음원 위치 추적 장치 및 그 방법 Download PDFInfo
- Publication number
- WO2014104815A1 WO2014104815A1 PCT/KR2013/012305 KR2013012305W WO2014104815A1 WO 2014104815 A1 WO2014104815 A1 WO 2014104815A1 KR 2013012305 W KR2013012305 W KR 2013012305W WO 2014104815 A1 WO2014104815 A1 WO 2014104815A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- sound source
- source section
- equation
- input signal
- wind noise
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000001514 detection method Methods 0.000 claims description 32
- 230000001131 transforming effect Effects 0.000 claims description 4
- 230000009467 reduction Effects 0.000 claims description 2
- 230000000694 effects Effects 0.000 description 6
- 230000008859 change Effects 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R29/00—Monitoring arrangements; Testing arrangements
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/188—Capturing isolated or intermittent images triggered by the occurrence of a predetermined event, e.g. an object reaching a predetermined position
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R3/00—Circuits for transducers, loudspeakers or microphones
- H04R3/002—Damping circuit arrangements for transducers, e.g. motional feedback circuits
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R3/00—Circuits for transducers, loudspeakers or microphones
- H04R3/005—Circuits for transducers, loudspeakers or microphones for combining the signals of two or more microphones
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0208—Noise filtering
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/78—Detection of presence or absence of voice signals
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R2410/00—Microphones
- H04R2410/07—Mechanical or electrical reduction of wind noise generated by wind passing a microphone
Definitions
- Embodiments relate to a sound source location tracking device and a method thereof, and more particularly to a sound source location tracking device and method in a wind noise environment.
- Sound source location technology for intelligent CCTV cameras in outdoor environments detects important sound events such as human screams and car cobblestones. It aims to keep the surroundings safer by notifying the security department.
- the outdoor environment is different from the general indoor environment and there are various random noises.
- noises such as passing motorcycles, engine sounds of cars, and wind noises.
- false alarms ie, misrecognition
- Wind noise is difficult to find any regular pattern information compared to other noises (e.g. automobile or motorcycle noise), and it is analyzed because of the difficulty of randomly changing various factors such as wind size and direction. .
- detecting a sound source section based on an average power value of the Fourier transformed input signal; Received by the first sound source section and microphone Detecting a second sound source section from which wind noise is removed based on a difference in power values for respective input signals; Detecting a position of a sound source based on a phase difference between the second sound source section and the input signal received by the plurality of microphones; Calculating a reliability of position detection of the sound source, wherein detecting the first sound source section further includes detecting the first sound source section only when the first sound source section is continuously connected.
- a sound source location tracking method is provided through wind noise reduction.
- the sound source location tracking method through the wind noise removing step of Fourier transform the input signal of the time domain received by the plurality of microphones; Detecting a first sound source section based on an average power value of the Fourier transformed input signal; Detecting a second sound source section from which wind noise is eliminated based on a difference between power values of respective input signals received by the first sound source section and the microphone; And detecting the position of the sound source based on the phase difference between the second sound source section and the input signal received by the plurality of microphones.
- the sound source location tracking method by removing the wind noise includes the step of calculating the reliability of the position detection of the sound source, the step of detecting the first sound source section is continuous the first sound source section It may be characterized in that it further comprises the step of detecting as the first sound source section only if continued.
- the sound source location tracking method by removing the wind noise is the agent
- the detecting of the one sound source section may include determining an average power value of the input signal using Equation 1 below, and determining the one sound source section using Equation 2 below, wherein n is a frame index.
- F rain is the minimum frequency of the input signal
- f max is the maximum frequency of the input signal
- Nf is characterized in that the number of frequency bins between the minimum frequency (f min ) to the maximum frequency (f max ). Equations 2 and 2 are represented in the following description.
- the sound source location tracking method by removing the wind noise, the i rain is 300Hz
- the f raax may be characterized in that the 3.4kHz.
- the step of detecting the second sound source section to obtain the power difference value between the channel using the equation (4) of the specification, using the equation (5) of the specification Determine the presence of wind noise, where P represents the number of microphone pairs, and ⁇ - 2 is 5dB.
- the sound source position tracking device through the wind noise removal, a plurality of microphones; A Fourier transform unit for Fourier transforming input signals in a time domain received by the plurality of microphones; A first sound source section detector for detecting a first sound source section based on the average power value of the Fourier transformed input signal; A second sound source section detector for detecting a second sound source section from which wind noise is removed based on a difference between power values of input signals received by the first sound source section and the microphone; And a sound source position detector for detecting the position of the sound source based on the phase difference between the two sound source sections and the input signals received by the plurality of microphones.
- the sound source position tracking device by removing the wind noise includes a reliability calculation unit for calculating the reliability of the position detection of the sound source, the first sound source section detector, the first sound source section is continuous Only when the first sound source section can be characterized in that the detection.
- the sound source position tracking device by removing the wind noise, the first sound source section detection unit, the average power value of the input signal is determined using Equation 1 below, the first sound source section is In Equation 1 and Equation 2, n is the frame index, i rain is the minimum frequency of the input signal, i max is the maximum frequency of the input signal, Nf is the minimum frequency (f min ) Is the number of frequency bins between the highest frequency (f raax ).
- the sound source location tracking device by removing the wind noise, the f rain is 300Hz, the f max may be characterized in that 3.4kHz.
- the sound source position tracking device by removing the wind noise, the second sound source section detection unit, to obtain the power difference value between the channel using Equation 3 below, using the following Equation 4 of the wind noise
- P represents the number of microphone pairs (microphone pair)
- TH- 2 may be characterized in that 5dB.
- a plurality of microphones A Fourier transform unit for Fourier transforming the input signal in the time domain received by the plurality of microphones; A first sound source section detector for detecting a first sound source section based on the average power value of the Fourier transformed input signal; A second sound source section detector for detecting a second sound source section from which wind noise is removed based on a difference between the U sound source section and a power value for each input signal received by the microphone; Based on the phase difference between the second sound source section and the input signal received by the plurality of microphones A sound source position detector for detecting a position of the sound source; And a reliability calculator configured to calculate a reliability of position detection of the sound source, wherein the first sound source section detector detects the first sound source section only when the first sound source section continues continuously. Sound source location tracking device is provided through.
- FIG. 1 is a flowchart of a sound source location tracking method according to an embodiment of the present invention.
- Figure 2 is a spectrogram comparison of the input signal of the microphone according to an embodiment of the present invention.
- FIG. 3 is a flowchart illustrating a sound source location tracking method according to an embodiment of the present invention.
- 4 is a diagram illustrating wind noise sections and screams in a spectrogram comparison diagram of input signals of a microphone according to an exemplary embodiment of the present invention.
- 5 is a log-power change graph of an input signal of a conventional microphone.
- FIG. 6 is a graph showing a sound source section detection result for the input signal of a conventional microphone.
- FIG. 7 is a log-power change graph for an input signal of a microphone according to an embodiment of the present invention.
- FIG. 8 is a graph illustrating a result of detecting a wind noise section for an input signal of a microphone according to an exemplary embodiment of the present invention.
- FIG. 9 is a graph showing a result of detecting a sound source section for the input signal of the microphone according to an embodiment of the present invention.
- FIG. 10 is a graph illustrating a result of detecting a sound source section after reflecting an input signal of a microphone, a sound source section detection result, and reliability and clustering according to an embodiment of the present invention.
- Embodiments described herein may have aspects that are wholly hardware, partly hardware and partly software, or wholly software. have.
- "unit”, “module”, “device” or “system” and the like refer to a computer-related entity such as hardware, a combination of hardware and software, or software.
- parts, modules, devices, or systems herein refer to running processes, processors, objects, executables, threads of execution, programs, and / or computers. may be, but is not limited to.
- both an application running on a computer and a computer may correspond to a part, module, device or system of the present disclosure.
- Embodiments have been described with reference to the flowchart presented in the drawings. For simplicity, the method is shown and described as a series of blocks, but the present invention is not limited to the order of the blocks, and some of the blocks are in a different order or simultaneously with other blocks than those shown and described herein. Various other branches, flow paths, and blocks may be implemented to achieve the same or similar results. In addition, not all illustrated blocks may be required for implementation of the method described herein. Furthermore, the method according to an embodiment of the present invention may be implemented in the form of a computer program for performing a series of processes, and the computer program may be recorded on a computer-readable recording medium.
- FIG. 1 is a flowchart of a sound source location tracking method according to an embodiment of the present invention.
- STFT short-term frequency transform
- VAD Voice Activity Detection
- the wind detection and remover (WDR) processor performs a wind detection and removal step of determining whether the current frame is wind noise using a multi-channel signal in the time domain. Because wind noise generally has a large energy value, most of them are detected in the sound source section, which causes a lot of misdirection detection. Therefore, because WDR processing is performed, frames corresponding to wind noise are excluded from the VAD detection result, so that sound source direction detection can be performed only on sound event frames. In addition, even for very short impulse sound sources (generally meaningless sounds in this case), this system estimates the estimated reliability of the input source and the duration of the sound source section detection (the frames that are continuously determined by the sound source section). By setting a reasonable reference value, clustering is performed only for sound source events that meet the cumulative condition, and the position (horizontal angle and altitude angle) for the corresponding sound source event is output.
- WDR wind detection and remover
- the position (horizontal angle, elevation angle) value of the sound source event generated is transmitted and controlled to the camera through the HTTP protocol of the IP camera.
- VAD Volt Activity Detection
- Equation 1 The power value in the frequency domain for the nth frame can be obtained as shown in Equation 1.
- the wind noise has a characteristic that the strength reaching each microphone has a different characteristic.
- the average power value of the input signal is calculated by using the average of the input power values of all channels as shown in Equation 1.
- f min and f nax are the minimum frequency (300 Hz) and the maximum frequency (3.4 kHz).
- ⁇ represents the number of frequency bins between the minimum frequency (fmin) and the highest frequency (imax).
- P noise (n) and ⁇ are the background noise power for the ⁇ -th frame and the sound source detection reference value (ie, 3 dB). That is, when the difference between the power value of the current frame and the background noise power value is greater than the reference value TH, it is determined that the sound source is present, whereas if the difference is small, the sound source does not exist.
- Equation 3 the performance of sound source section detection is highly dependent on the prediction accuracy of background noise power.
- adaptive noise estimation method using temporal change is used. That is, this is shown in Equation 3.
- estimation factors al and a 2 are set to 0.95 and 0.99, respectively. This is merely an example.
- Wind noise has a characteristic that the frequency distribution between channels (microphones) is much different from that of human voices or general noise. That is, as shown in the circle of the microphone 1 and 2 as shown in Figure 2 it can be seen that the energy distribution for each frequency of each channel at the same time is very different. Therefore, using this feature, it is possible to effectively solve the problem of vulnerable to wind noise response of the sound source section detection (VAD) part using only existing energy information.
- VAD sound source section detection
- Wind Detection and Remover is performed by defining cross-channel different power (XDP) as a measure of wind noise as shown in Equation 4.
- XDP cross-channel different power
- Equation 5 the magnitude of the reference value ( ⁇ 3 ⁇ 4) was set to 5 dB.
- Equation 6 the results of Equation 2 and Equation 5 are combined as shown in Equation 6.
- Equation 7 Rearranging Equation 6 can be solved as in Equation 7.
- FIG. 4 a sound source section detection test was performed using real sound source data in which wind noise and scream sound exist simultaneously.
- the conventional VAD method after selecting an arbitrary channel among the multi-channel input signals, calculating the log-power value (Fig. 4) using Equation 1, it can be confirmed that the sound source section is detected as shown in Fig. 5. have.
- the wind noise section also has a high power value, and thus is mostly detected as a meaningful sound source section. I can confirm that there is.
- the power difference value between the channels is shown in the graph as shown in FIG. 7. Therefore, when the existence of wind is determined using Equation 5, the presence of wind noise is shown in FIG. 8. It can be confirmed that is detected correctly. Therefore, when the result is combined with the sound source section determined by the existing VAD method using the equation (6), the wind noise section is accurately excluded as shown in FIG. 9, and other important event sounds (for example, the section of the human screams) are maintained. It could be confirmed.
- Equation 8 a phase difference between channels of each frequency with respect to the input sound source signal may be calculated as shown in Equation 8.
- Equation 10 ⁇ (f) ⁇ (ij) ⁇ (M) ⁇ (M) ⁇ (M) ⁇ (M)
- Equation 11 is used to calculate the position and reliability score of the input source. That is, the positions (horizontal angle and altitude angle) of the corresponding input sound source are calculated from the index ( ⁇ , ⁇ ) and the maximum reliability s (n), which are the maximum values of Equation (10).
- Equation 11 ⁇ ( ⁇ ), ⁇ ( ⁇ ), s ( «) ⁇ argmax C ( ⁇ , ⁇ , ⁇ )
- the position of the sound source section (that is, viewed as an event) when the VAD detected frames are consecutively accumulated and a predetermined frame is accumulated
- the value is finally calculated and output using the clustering method.
- 10 shows the input signal (top) sound source section detection result (middle), direction detection result, and clustering result (bottom).
- FIG. 9 (top) shows the spectrogram of the input signal of the microphone # 1
- FIG. 9 (the middle) shows the result of detecting the final VAD section for the input signal.
- the result shows the horizontal angle (azimuth) for each frame as * (blue) in FIG.
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Otolaryngology (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Measurement Of Velocity Or Position Using Acoustic Or Ultrasonic Waves (AREA)
- Circuit For Audible Band Transducer (AREA)
- Quality & Reliability (AREA)
Abstract
Description
Claims
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US14/758,056 US9549271B2 (en) | 2012-12-28 | 2013-12-27 | Device and method for tracking sound source location by removing wind noise |
KR1020157017159A KR101681188B1 (ko) | 2012-12-28 | 2013-12-27 | 바람 소음 제거를 통한 음원 위치 추적 장치 및 그 방법 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR20120155967 | 2012-12-28 | ||
KR10-2012-0155967 | 2012-12-28 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2014104815A1 true WO2014104815A1 (ko) | 2014-07-03 |
Family
ID=51021754
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/KR2013/012305 WO2014104815A1 (ko) | 2012-12-28 | 2013-12-27 | 바람 소음 제거를 통한 음원 위치 추적 장치 및 그 방법 |
Country Status (3)
Country | Link |
---|---|
US (1) | US9549271B2 (ko) |
KR (1) | KR101681188B1 (ko) |
WO (1) | WO2014104815A1 (ko) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20170034405A (ko) * | 2014-07-21 | 2017-03-28 | 시러스 로직 인터내셔널 세미컨덕터 리미티드 | 바람 잡음 검출을 위한 방법 및 장치 |
US10516941B2 (en) | 2014-06-04 | 2019-12-24 | Cirrus Logic, Inc. | Reducing instantaneous wind noise |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110603587A (zh) | 2017-05-08 | 2019-12-20 | 索尼公司 | 信息处理设备 |
US11209831B2 (en) * | 2019-05-03 | 2021-12-28 | Ford Global Technologies, Llc | Object sound detection |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR100883712B1 (ko) * | 2006-08-09 | 2009-02-12 | 후지쯔 가부시끼가이샤 | 음원 방향 추정 방법, 및 음원 방향 추정 장치 |
US20110004470A1 (en) * | 2009-07-02 | 2011-01-06 | Mr. Alon Konchitsky | Method for Wind Noise Reduction |
US20110123044A1 (en) * | 2003-02-21 | 2011-05-26 | Qnx Software Systems Co. | Method and Apparatus for Suppressing Wind Noise |
US20120148067A1 (en) * | 2008-12-05 | 2012-06-14 | Audioasics A/S | Wind noise detection method and system |
US20120191447A1 (en) * | 2011-01-24 | 2012-07-26 | Continental Automotive Systems, Inc. | Method and apparatus for masking wind noise |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7274794B1 (en) * | 2001-08-10 | 2007-09-25 | Sonic Innovations, Inc. | Sound processing system including forward filter that exhibits arbitrary directivity and gradient response in single wave sound environment |
US7895036B2 (en) * | 2003-02-21 | 2011-02-22 | Qnx Software Systems Co. | System for suppressing wind noise |
US8831936B2 (en) * | 2008-05-29 | 2014-09-09 | Qualcomm Incorporated | Systems, methods, apparatus, and computer program products for speech signal processing using spectral contrast enhancement |
US8724829B2 (en) * | 2008-10-24 | 2014-05-13 | Qualcomm Incorporated | Systems, methods, apparatus, and computer-readable media for coherence detection |
US9330675B2 (en) * | 2010-11-12 | 2016-05-03 | Broadcom Corporation | Method and apparatus for wind noise detection and suppression using multiple microphones |
CN103348686B (zh) * | 2011-02-10 | 2016-04-13 | 杜比实验室特许公司 | 用于风检测和抑制的系统和方法 |
EP2780906B1 (en) * | 2011-12-22 | 2016-09-14 | Cirrus Logic International Semiconductor Limited | Method and apparatus for wind noise detection |
-
2013
- 2013-12-27 KR KR1020157017159A patent/KR101681188B1/ko active IP Right Grant
- 2013-12-27 US US14/758,056 patent/US9549271B2/en active Active
- 2013-12-27 WO PCT/KR2013/012305 patent/WO2014104815A1/ko active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110123044A1 (en) * | 2003-02-21 | 2011-05-26 | Qnx Software Systems Co. | Method and Apparatus for Suppressing Wind Noise |
KR100883712B1 (ko) * | 2006-08-09 | 2009-02-12 | 후지쯔 가부시끼가이샤 | 음원 방향 추정 방법, 및 음원 방향 추정 장치 |
US20120148067A1 (en) * | 2008-12-05 | 2012-06-14 | Audioasics A/S | Wind noise detection method and system |
US20110004470A1 (en) * | 2009-07-02 | 2011-01-06 | Mr. Alon Konchitsky | Method for Wind Noise Reduction |
US20120191447A1 (en) * | 2011-01-24 | 2012-07-26 | Continental Automotive Systems, Inc. | Method and apparatus for masking wind noise |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10516941B2 (en) | 2014-06-04 | 2019-12-24 | Cirrus Logic, Inc. | Reducing instantaneous wind noise |
KR20170034405A (ko) * | 2014-07-21 | 2017-03-28 | 시러스 로직 인터내셔널 세미컨덕터 리미티드 | 바람 잡음 검출을 위한 방법 및 장치 |
EP3172906A4 (en) * | 2014-07-21 | 2018-01-10 | Cirrus Logic International Semiconductor Limited | Method and apparatus for wind noise detection |
KR102313894B1 (ko) * | 2014-07-21 | 2021-10-18 | 시러스 로직 인터내셔널 세미컨덕터 리미티드 | 바람 잡음 검출을 위한 방법 및 장치 |
Also Published As
Publication number | Publication date |
---|---|
US20150358750A1 (en) | 2015-12-10 |
KR101681188B1 (ko) | 2016-12-02 |
KR20150100704A (ko) | 2015-09-02 |
US9549271B2 (en) | 2017-01-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Foggia et al. | Audio surveillance of roads: A system for detecting anomalous sounds | |
JP5862679B2 (ja) | 音源検出装置 | |
JP4545233B2 (ja) | 音判定装置、音判定方法、及び、音判定プログラム | |
EP3203380B1 (en) | Multi-mode auxiliary data encoding in audio | |
JP2020509703A (ja) | 対象音を検出するためのシステムおよび方法 | |
KR101759143B1 (ko) | 음향 추적 정보 제공 방법, 차량용 음향 추적 장치, 및 이를 포함하는 차량 | |
EP2637167A1 (en) | Endpoint detection apparatus for sound source and method thereof | |
WO2014104815A1 (ko) | 바람 소음 제거를 통한 음원 위치 추적 장치 및 그 방법 | |
Lim et al. | Robust sound event classification using LBP-HOG based bag-of-audio-words feature representation. | |
WO2014102938A1 (ja) | 音検知装置及び音検知方法 | |
JPWO2009044509A1 (ja) | 音源方向検知装置 | |
US20140350923A1 (en) | Method and device for detecting noise bursts in speech signals | |
Andersson et al. | Fusion of acoustic and optical sensor data for automatic fight detection in urban environments | |
JP2003195882A (ja) | 信号処理システムおよび方法 | |
CN110673096A (zh) | 语音定位方法和装置、计算机可读存储介质、电子设备 | |
US20190281386A1 (en) | Apparatus and a method for unwrapping phase differences | |
Hilal et al. | A distributed sensor management for large-scale IoT indoor acoustic surveillance | |
Xia et al. | Csafe: An intelligent audio wearable platform for improving construction worker safety in urban environments | |
CN108965789B (zh) | 一种无人机监测方法及音视频联动装置 | |
KR20120130371A (ko) | Gmm을 이용한 응급 단어 인식 방법 | |
CN108063890A (zh) | 一种监控设备控制方法及装置 | |
US20070038448A1 (en) | Objection detection by robot using sound localization and sound based object classification bayesian network | |
Qi et al. | A low-cost driver and passenger activity detection system based on deep learning and multiple sensor fusion | |
CN110890104B (zh) | 语音端点检测方法及系统 | |
Salvati et al. | A real-time system for multiple acoustic sources localization based on ISP comparison |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 13868270 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 20157017159 Country of ref document: KR Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 14758056 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 13868270 Country of ref document: EP Kind code of ref document: A1 |