[go: up one dir, main page]

FR3103660B1 - Method and device for processing an audio signal - Google Patents

Method and device for processing an audio signal Download PDF

Info

Publication number
FR3103660B1
FR3103660B1 FR1913207A FR1913207A FR3103660B1 FR 3103660 B1 FR3103660 B1 FR 3103660B1 FR 1913207 A FR1913207 A FR 1913207A FR 1913207 A FR1913207 A FR 1913207A FR 3103660 B1 FR3103660 B1 FR 3103660B1
Authority
FR
France
Prior art keywords
audio signal
processing
signal
vector
tuner
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
FR1913207A
Other languages
French (fr)
Other versions
FR3103660A1 (en
Inventor
Farhan Mirani
Yuehgoh Foutse
Hugo Levard
Sabrine Lazrak
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Stellantis Auto Sas Fr
Original Assignee
PSA Automobiles SA
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by PSA Automobiles SA filed Critical PSA Automobiles SA
Priority to FR1913207A priority Critical patent/FR3103660B1/en
Priority to PCT/FR2020/051901 priority patent/WO2021105574A1/en
Priority to EP20807468.2A priority patent/EP4066389A1/en
Publication of FR3103660A1 publication Critical patent/FR3103660A1/en
Application granted granted Critical
Publication of FR3103660B1 publication Critical patent/FR3103660B1/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B1/00—Details of transmission systems, not covered by a single one of groups H04B3/00 - H04B13/00; Details of transmission systems not characterised by the medium used for transmission
    • H04B1/06—Receivers
    • H04B1/08—Constructional details, e.g. cabinet
    • H04B1/082—Constructional details, e.g. cabinet to be used in vehicles
    • 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
    • G10L25/27—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique
    • G10L25/30—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique using neural networks
    • 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
    • G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
    • 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
    • G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
    • G10L25/21—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters the extracted parameters being power information

Landscapes

  • Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Human Computer Interaction (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Fittings On The Vehicle Exterior For Carrying Loads, And Devices For Holding Or Mounting Articles (AREA)

Abstract

L’invention concerne un procédé et un dispositif de traitement d’un signal audio, par exemple un signal reçu par un véhicule (103) et convertit dans un tuner (104). A cet effet, le signal audio est échantillonné pour obtenir un vecteur de valeurs d’amplitudes chacune associée à un échantillon du signal. Le vecteur d’entrée est passé dans une pluralité de couches de convolution d’un réseau de neurones pour obtenir en sortie une classification du signal audio, une classe représentative d’un niveau de bruit étant attribuée au signal audio. Figure pour l’abrégé : Figure 1The invention relates to a method and a device for processing an audio signal, for example a signal received by a vehicle (103) and converted in a tuner (104). To this end, the audio signal is sampled to obtain a vector of amplitude values each associated with a sample of the signal. The input vector is passed through a plurality of convolutional layers of a neural network to output a classification of the audio signal, with a class representative of a noise level assigned to the audio signal. Figure for the abstract: Figure 1

FR1913207A 2019-11-26 2019-11-26 Method and device for processing an audio signal Active FR3103660B1 (en)

Priority Applications (3)

Application Number Priority Date Filing Date Title
FR1913207A FR3103660B1 (en) 2019-11-26 2019-11-26 Method and device for processing an audio signal
PCT/FR2020/051901 WO2021105574A1 (en) 2019-11-26 2020-10-21 Method and device for processing an audio signal
EP20807468.2A EP4066389A1 (en) 2019-11-26 2020-10-21 Method and device for processing an audio signal

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
FR1913207 2019-11-26
FR1913207A FR3103660B1 (en) 2019-11-26 2019-11-26 Method and device for processing an audio signal

Publications (2)

Publication Number Publication Date
FR3103660A1 FR3103660A1 (en) 2021-05-28
FR3103660B1 true FR3103660B1 (en) 2021-10-15

Family

ID=70228115

Family Applications (1)

Application Number Title Priority Date Filing Date
FR1913207A Active FR3103660B1 (en) 2019-11-26 2019-11-26 Method and device for processing an audio signal

Country Status (3)

Country Link
EP (1) EP4066389A1 (en)
FR (1) FR3103660B1 (en)
WO (1) WO2021105574A1 (en)

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6453251B1 (en) 1999-10-07 2002-09-17 Receptec Llc Testing method for components with reception capabilities
US9973849B1 (en) * 2017-09-20 2018-05-15 Amazon Technologies, Inc. Signal quality beam selection
GB2567503A (en) * 2017-10-13 2019-04-17 Cirrus Logic Int Semiconductor Ltd Analysing speech signals
KR102556098B1 (en) * 2017-11-24 2023-07-18 한국전자통신연구원 Method and apparatus of audio signal encoding using weighted error function based on psychoacoustics, and audio signal decoding using weighted error function based on psychoacoustics

Also Published As

Publication number Publication date
FR3103660A1 (en) 2021-05-28
EP4066389A1 (en) 2022-10-05
WO2021105574A1 (en) 2021-06-03

Similar Documents

Publication Publication Date Title
EP0932964B1 (en) Method and device for blind equalizing of transmission channel effects on a digital speech signal
CN111678599A (en) Laser spectral noise reduction method and device based on deep learning optimization of S-G filtering
FR3103660B1 (en) Method and device for processing an audio signal
FR3096782B1 (en) : Method and device for identifying atomic species emitting X or gamma radiation
CN118656582B (en) Method for eliminating organic light-emitting display noise with driving circuit
US4388711A (en) Optimum flow noise cancelling hydrophone module
CN109557587A (en) A kind of VSP seismic data tube wave frequency filtering method and device
FR2698470A1 (en) Continuous monitoring in real=time of complex fabrication process e.g photographic film mfr - uses local monitoring of process data to send data to central station for conversion to frequency variation to allow testing.
CN1033323A (en) Seismic acquisition system and method with increased bandwidth
US20190028130A1 (en) Method and Device for Processing a Signal
CN114417529B (en) Method and device for mechanically pumping to adjust equivalent Q value of silicon microresonator RC system
CN113053354B (en) Method and equipment for improving voice synthesis effect
CN1355916A (en) Signal-to-noise reduction by time-domain spectral subtraction
Chang On the filter problem of the power-spectrum analyzer
FR2830328A1 (en) DEVICE AND METHOD FOR ANALYZING THE STRUCTURE OF A MATERIAL
FR3091929B1 (en) Determination of the dispersion of an electronic component
US6519541B1 (en) Multiple frequency signal detector
US6370482B1 (en) Method for automated diagnosis of diagnostic objects
FR3107367B1 (en) Transfer function measurement in a mechatronic system
CN115565523A (en) End-to-end channel quality evaluation method and system based on neural network
CN100340865C (en) Automatic testing method of filter
CN1710622A (en) An analog-to-digital conversion method and system based on voltage-frequency conversion and photoelectric isolation
FR3119257B1 (en) Method and device for recognizing manipulation of an exhaust gas post-treatment system
FR3110268B1 (en) Methods for secure use of a first neural network on an input datum, and for learning parameters of a second neural network
RU2690317C1 (en) Polyharmonic signal detection method

Legal Events

Date Code Title Description
PLFP Fee payment

Year of fee payment: 2

PLSC Publication of the preliminary search report

Effective date: 20210528

PLFP Fee payment

Year of fee payment: 3

PLFP Fee payment

Year of fee payment: 4

PLFP Fee payment

Year of fee payment: 5

CD Change of name or company name

Owner name: STELLANTIS AUTO SAS, FR

Effective date: 20240423

PLFP Fee payment

Year of fee payment: 6