Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020112577 - SIMILARITY MEASURE ASSISTED ADAPTATION CONTROL OF AN ECHO CANCELLER

Publication Number WO/2020/112577
Publication Date 04.06.2020
International Application No. PCT/US2019/062897
International Filing Date 24.11.2019
IPC
G10L 21/0208 2013.01
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
21Processing of the speech or voice signal to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
02Speech enhancement, e.g. noise reduction or echo cancellation
0208Noise filtering
G10L 25/48 2013.01
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
25Speech or voice analysis techniques not restricted to a single one of groups G10L15/-G10L21/129
48specially adapted for particular use
H04M 9/08 2006.01
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
MTELEPHONIC COMMUNICATION
9Arrangements for interconnection not involving centralised switching
08Two-way loud-speaking telephone systems with means for conditioning the signal, e.g.  for suppressing echoes for one or both directions of traffic
CPC
G06N 20/00
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
G10L 2021/02082
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
21Processing of the speech or voice signal to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
02Speech enhancement, e.g. noise reduction or echo cancellation
0208Noise filtering
02082the noise being echo, reverberation of the speech
G10L 21/0208
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
21Processing of the speech or voice signal to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
02Speech enhancement, e.g. noise reduction or echo cancellation
0208Noise filtering
G10L 21/0224
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
21Processing of the speech or voice signal to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
02Speech enhancement, e.g. noise reduction or echo cancellation
0208Noise filtering
0216characterised by the method used for estimating noise
0224Processing in the time domain
G10L 25/48
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
25Speech or voice analysis techniques not restricted to a single one of groups G10L15/00-G10L21/00
48specially adapted for particular use
H04M 9/082
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
MTELEPHONIC COMMUNICATION
9Interconnection arrangements not involving centralised switching
08Two-way loud-speaking telephone systems with means for suppressing echoes or otherwise conditioning for one or other direction of traffic
082using echo cancellers
Applicants
  • MICROSOFT TECHNOLOGY LICENSING, LLC [US]/[US]
Inventors
  • SØRENSEN, Karsten Vandborg
  • RANA, Puneet
Agents
  • MINHAS, Sandip S.
  • ADJEMIAN, Monica
  • BARKER, Doug
  • CHATTERJEE, Aaron C.
  • CHEN, Wei-Chen Nicholas
  • CHOI, Daniel
  • CHURNA, Timothy
  • DINH, Phong
  • EVANS, Patrick
  • GABRYJELSKI, Henry
  • GOLDSMITH, Micah P.
  • GUPTA, Anand
  • HINOJOSA-SMITH, Brianna L.
  • HWANG, William C.
  • JARDINE, John S.
  • LEE, Sunah
  • LEMMON, Marcus
  • MARQUIS, Thomas
  • MEYERS, Jessica
  • ROPER, Brandon
  • SPELLMAN, Steven
  • SULLIVAN, Kevin
  • SWAIN, Cassandra T.
  • TABOR, Ben
  • WALKER, Matt
  • WIGHT, Stephen A.
  • WISDOM, Gregg
  • WONG, Ellen
  • WONG, Thomas S.
  • ZHANG, Hannah
  • TRAN, Kimberly
Priority Data
16/206,21330.11.2018US
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) SIMILARITY MEASURE ASSISTED ADAPTATION CONTROL OF AN ECHO CANCELLER
(FR) COMMANDE D'ADAPTATION ASSISTÉE PAR MESURE DE SIMILARITÉ D'UN ANNULEUR D'ÉCHO
Abstract
(EN)
Techniques for real-time audio communication including supplying an initial audio signal to an audio signal processor configured to process the initial audio signal and output a processed audio signal to an audio output means, obtaining a loopback audio signal corresponding to the processed audio signal, generating a plurality of audio features for the initial audio signal and the loopback audio signal, generating a similarity measure estimating a similarity of the initial audio signal to the first loopback audio signal based on at least the plurality of audio features, adjusting an adaptation rate for an audio signal processing operation based on at least the similarity measure, and controlling, based on at least the adjusted adaptation rate, an echo cancellation process for cancelling an estimated echo from a near-end audio signal received via an audio input means in proximity to the audio output means.
(FR)
L'invention concerne des techniques de communication audio en temps réel, consistant à envoyer un signal audio initial à un processeur de signal audio configuré pour traiter le signal audio initial et délivrer en sortie un signal audio traité à un élément de sortie audio, à obtenir un signal audio de bouclage correspondant au signal audio traité, à générer une pluralité de caractéristiques audio pour le signal audio initial et le signal audio de bouclage, à générer une mesure de similarité estimant une similarité du signal audio initial au premier signal audio de bouclage sur la base d'au moins la pluralité de caractéristiques audio, à ajuster un taux d'adaptation pour une opération de traitement de signal audio sur la base d'au moins la mesure de similarité, et à commander, sur la base au moins du taux d'adaptation ajusté, un processus d'annulation d'écho pour annuler un écho estimé à partir d'un signal audio d'extrémité proche reçu par l'intermédiaire d'un élément d'entrée audio à proximité de l'élément de sortie audio.
Also published as
Latest bibliographic data on file with the International Bureau