GB2465910B - Method and device for low-latency auditory model-based single-channel speech enhancement - Google Patents

Method and device for low-latency auditory model-based single-channel speech enhancement

Info

Publication number
GB2465910B
GB2465910B GB1004090.5A GB201004090A GB2465910B GB 2465910 B GB2465910 B GB 2465910B GB 201004090 A GB201004090 A GB 201004090A GB 2465910 B GB2465910 B GB 2465910B
Authority
GB
United Kingdom
Prior art keywords
low
based single
speech enhancement
auditory model
channel speech
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.)
Expired - Fee Related
Application number
GB1004090.5A
Other versions
GB201004090D0 (en
GB2465910A (en
Inventor
Martin Opitz
Robert Ha Ldrich
Franz Zotter
Markus Noisternig
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.)
AKG Acoustics GmbH
Original Assignee
AKG Acoustics GmbH
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 AKG Acoustics GmbH filed Critical AKG Acoustics GmbH
Publication of GB201004090D0 publication Critical patent/GB201004090D0/en
Publication of GB2465910A publication Critical patent/GB2465910A/en
Application granted granted Critical
Publication of GB2465910B publication Critical patent/GB2465910B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • 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
    • 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
    • G10L21/0216—Noise filtering characterised by the method used for estimating noise
    • 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
    • G10L21/0216—Noise filtering characterised by the method used for estimating noise
    • G10L21/0232—Processing in the frequency domain
    • 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
    • G10L21/0264—Noise filtering characterised by the type of parameter measurement, e.g. correlation techniques, zero crossing techniques or predictive techniques

Landscapes

  • Engineering & Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Quality & Reliability (AREA)
  • Signal Processing (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Compression, Expansion, Code Conversion, And Decoders (AREA)
  • Circuit For Audible Band Transducer (AREA)
GB1004090.5A 2007-10-02 2007-10-02 Method and device for low-latency auditory model-based single-channel speech enhancement Expired - Fee Related GB2465910B (en)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/AT2007/000466 WO2009043066A1 (en) 2007-10-02 2007-10-02 Method and device for low-latency auditory model-based single-channel speech enhancement

Publications (3)

Publication Number Publication Date
GB201004090D0 GB201004090D0 (en) 2010-04-28
GB2465910A GB2465910A (en) 2010-06-09
GB2465910B true GB2465910B (en) 2012-02-15

Family

ID=39447761

Family Applications (1)

Application Number Title Priority Date Filing Date
GB1004090.5A Expired - Fee Related GB2465910B (en) 2007-10-02 2007-10-02 Method and device for low-latency auditory model-based single-channel speech enhancement

Country Status (4)

Country Link
AT (1) AT509570B1 (en)
DE (1) DE112007003674T5 (en)
GB (1) GB2465910B (en)
WO (1) WO2009043066A1 (en)

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102011004338B3 (en) * 2011-02-17 2012-07-12 Siemens Medical Instruments Pte. Ltd. Method and device for estimating a noise
CN102157156B (en) * 2011-03-21 2012-10-10 清华大学 Single-channel voice enhancement method and system
US9173025B2 (en) 2012-02-08 2015-10-27 Dolby Laboratories Licensing Corporation Combined suppression of noise, echo, and out-of-location signals
EP2747081A1 (en) * 2012-12-18 2014-06-25 Oticon A/s An audio processing device comprising artifact reduction
EP3152756B1 (en) 2014-06-09 2019-10-23 Dolby Laboratories Licensing Corporation Noise level estimation
CN110580910B (en) * 2018-06-08 2024-04-26 北京搜狗科技发展有限公司 Audio processing method, device, equipment and readable storage medium
US10939161B2 (en) 2019-01-31 2021-03-02 Vircion LLC System and method for low-latency communication over unreliable networks
CN111063366A (en) * 2019-12-26 2020-04-24 紫光展锐(重庆)科技有限公司 Method and device for reducing noise, electronic equipment and readable storage medium
CN112151060B (en) * 2020-09-25 2022-11-25 展讯通信(天津)有限公司 Single-channel voice enhancement method and device, storage medium and terminal

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2002011125A1 (en) * 2000-07-31 2002-02-07 Herterkom Gmbh Attenuation of background noise and echoes in audio signal
EP1600947A2 (en) * 2004-05-26 2005-11-30 Honda Research Institute Europe GmbH Subtractive cancellation of harmonic noise
WO2006114100A1 (en) * 2005-04-26 2006-11-02 Aalborg Universitet Estimation of signal from noisy observations
EP1729287A1 (en) * 1999-01-07 2006-12-06 Tellabs Operations, Inc. Method and apparatus for adaptively suppressing noise

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6052771A (en) 1998-01-20 2000-04-18 International Business Machines Corporation Microprocessor with pipeline synchronization
EP1131892B1 (en) 1998-11-13 2006-08-02 Bitwave Private Limited Signal processing apparatus and method
US6377637B1 (en) * 2000-07-12 2002-04-23 Andrea Electronics Corporation Sub-band exponential smoothing noise canceling system

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1729287A1 (en) * 1999-01-07 2006-12-06 Tellabs Operations, Inc. Method and apparatus for adaptively suppressing noise
WO2002011125A1 (en) * 2000-07-31 2002-02-07 Herterkom Gmbh Attenuation of background noise and echoes in audio signal
EP1600947A2 (en) * 2004-05-26 2005-11-30 Honda Research Institute Europe GmbH Subtractive cancellation of harmonic noise
WO2006114100A1 (en) * 2005-04-26 2006-11-02 Aalborg Universitet Estimation of signal from noisy observations

Non-Patent Citations (7)

* Cited by examiner, † Cited by third party
Title
AMIR HUSSAIN et al: Nonlinear adaptive speech enhancement inspired by Early Auditory Processing. NONLINEAR SPEECH MODELING AND APPLICATIONS LECTURENOTES INCOMPUTER SCIENCE: LECTRIRE NOTES IN ARTIFICIAL INTELLIGENCE: LNCS SPRINGER-VERLAG, BE. VOL 3445, 1 JANUARY 2005, pages 291-316, XP019012535. *
Broad Band Acoustic Noise Reduction Using a Novel Frequency Depended Parametric Wiener Filter. *
JAN SCOGLUND et al: On time frequency masking in voiced speech IEEE transactions on speech and audio processing. IEEE service centre, New York, vol. 8 no.4 1 July 2000. XP011054031. ISSN 1063-6676. *
JOHNSON et al: Speech signal enhancement through adaptive wavelet thresholding. SPEECH COMMUNICATION, ELSEVIER SCIENCE PUBLISHERS AMSTERDAM, NL. VOL 49, NO. 2. 15 February 2001, pages 123-133. XP005890520. *
KALLIRIS M G et al: Broad band acoustic noise reduction using a novel frequency depended parametric wiener filter. IMPLEMNETATIONS USING FILTERBANK, STFF AND WAVELET ANALYSIS/SYNTHESIS TECHNIQUES. AUDIO ENGINEERING SOCIETY (AES) CONVENTION, 12 MAY 2001-15 MAY 2001 PAGES 1-9 XP002499667, AMSTERDAM. *
LIN et al: Speech denoising based on an auditory filterbank' SIGNAL PROCESSING 2002 6TH INTERNATIONAL CONFERENCE ON AUG 26-30 2002, PISCATAWAY, NJ, USA IEEE. VOL 1 26 AUGUST 2002 PAGES 552-555, XP010628047 *
Speech denoising based on an auditory filterbank. *

Also Published As

Publication number Publication date
GB201004090D0 (en) 2010-04-28
AT509570A5 (en) 2011-09-15
GB2465910A (en) 2010-06-09
AT509570B1 (en) 2011-12-15
DE112007003674T5 (en) 2010-08-12
WO2009043066A1 (en) 2009-04-09

Similar Documents

Publication Publication Date Title
GB2465910B (en) Method and device for low-latency auditory model-based single-channel speech enhancement
HK1132831A1 (en) Method and system for providing speech recognition
TWI349878B (en) Methods and apparatus for improved voice recognition and voice recognition systems
EP2301022A4 (en) Multi-reference lpc filter quantization and inverse quantization device and method
EP2262278A4 (en) Speech processing device
GB2482630B (en) A speech processing method and apparatus
EP2061255A4 (en) Information processing device and method
EP2157540A4 (en) Information processing device and information processing method
EP2120447A4 (en) Information processing device and method
TWI367564B (en) Lateral dmos device structure and fabrication method therefor
EP2482277A4 (en) Method for identifying a speaker based on random speech phonograms using formant equalization
EP2197214A4 (en) Method and device for reducing block distortion
EP2339444A4 (en) Information processing device and information processing method
EP2312459A4 (en) Information processing device and information processing method
TWI349266B (en) Voice recognition system and method
GB0920480D0 (en) Speech processing and learning
GB2451907B (en) Device for modifying and improving the behaviour of speech recognition systems
TWI346851B (en) Information processing device and information processing method
EP2402868A4 (en) Speech search device and speech search method
TWI372365B (en) Method and apparatus for directional edge enhancement
EP2199743A4 (en) Mounted-on-a-car instrument and utterance priority method
EP2096630A4 (en) Audio recognition device and audio recognition method
HK1122173A1 (en) Method and device for releasing speaking right
EP2226706A4 (en) Information processing device and information processing method
TWI349925B (en) Speech recognition device and method thereof

Legal Events

Date Code Title Description
PCNP Patent ceased through non-payment of renewal fee

Effective date: 20191002