EP1926087A1 - Adaptation d'un dispositif auditif à un signal vocal - Google Patents

Adaptation d'un dispositif auditif à un signal vocal Download PDF

Info

Publication number
EP1926087A1
EP1926087A1 EP07121483A EP07121483A EP1926087A1 EP 1926087 A1 EP1926087 A1 EP 1926087A1 EP 07121483 A EP07121483 A EP 07121483A EP 07121483 A EP07121483 A EP 07121483A EP 1926087 A1 EP1926087 A1 EP 1926087A1
Authority
EP
European Patent Office
Prior art keywords
speaker
analysis result
hearing
speech signal
signal
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.)
Ceased
Application number
EP07121483A
Other languages
German (de)
English (en)
Inventor
Volkmar Hamacher
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.)
Sivantos GmbH
Original Assignee
Siemens Audioligische Technik 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 Siemens Audioligische Technik GmbH filed Critical Siemens Audioligische Technik GmbH
Publication of EP1926087A1 publication Critical patent/EP1926087A1/fr
Ceased legal-status Critical Current

Links

Images

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
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
    • H04R25/00—Deaf-aid sets, i.e. electro-acoustic or electro-mechanical hearing aids; Electric tinnitus maskers providing an auditory perception
    • H04R25/70—Adaptation of deaf aid to hearing loss, e.g. initial electronic fitting
    • 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
    • G10L21/06—Transformation of speech into a non-audible representation, e.g. speech visualisation or speech processing for tactile aids
    • G10L2021/065—Aids for the handicapped in understanding
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
    • H04R2225/00—Details of deaf aids covered by H04R25/00, not provided for in any of its subgroups
    • H04R2225/41—Detection or adaptation of hearing aid parameters or programs to listening situation, e.g. pub, forest
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
    • H04R2225/00—Details of deaf aids covered by H04R25/00, not provided for in any of its subgroups
    • H04R2225/43—Signal processing in hearing aids to enhance the speech intelligibility

Definitions

  • the present invention relates to a fitting method for adapting a hearing device to a user.
  • the present invention relates to a corresponding matching device and a method for operating the hearing device and the hearing device itself.
  • hearing device is understood here in particular a hearing aid, but also a headset, a headset and the like.
  • Hearing aids are portable hearing aids that are used to care for the hearing impaired.
  • different types of hearing aids such as behind-the-ear hearing aids (BTE), in-the-ear hearing aids (IDO) and Concha hearing aids are provided.
  • BTE behind-the-ear hearing aids
  • IDO in-the-ear hearing aids
  • Concha hearing aids are provided.
  • the hearing aids listed by way of example are worn on the outer ear or in the ear canal.
  • bone conduction hearing aids, implantable or vibrotactile hearing aids are also available on the market. The stimulation of the damaged hearing takes place either mechanically or electrically.
  • Hearing aids have in principle as essential components an input transducer, an amplifier and an output transducer.
  • the input transducer is usually a sound receiver, z. As a microphone, and / or an electromagnetic receiver, for. B. an induction coil.
  • the output transducer is usually used as an electroacoustic transducer, z. As miniature speaker, or as an electromechanical transducer, z. B. bone conduction, realized.
  • the amplifier is usually integrated in a signal processing unit. This basic structure is in FIG. 1 shown using the example of a behind-the-ear hearing aid. In a hearing aid housing 1 for carrying behind the ear, one or more microphones 2 for receiving the sound from the environment are installed.
  • a signal processing unit 3 also in the hearing aid housing 1, processes the microphone signals and amplifies them.
  • the output signal of the signal processing unit 3 is transmitted to a loudspeaker or earpiece 4, which outputs an acoustic signal.
  • the sound is optionally transmitted via a sound tube, which is fixed with an earmold in the ear canal, to the eardrum of the device carrier.
  • the power supply of the hearing device and in particular of the signal processing unit 3 is carried out by a likewise integrated into the hearing aid housing 1 battery. 5
  • Speech understanding in an environment filled with noise is still the biggest problem hearing professionals face today. This means that the noise suppression in hearing aids must be further improved. This applies in particular to the noise reduction algorithms in hearing aids without directional microphones.
  • the benefit of a higher quality spurious reduction technique is mainly in improving speech quality and reducing the annoyance of background disorders.
  • the main difficulty lies in the estimation of the noise components in the microphone signal. This is done today usually on a signal-statistical basis with stationarity as the sole criterion for separation. It is exploited that noise usually have a stationary envelope, whereas speech signals are unsteady. Further differentiating assumptions regarding both signals are not made.
  • the signal analysis comprises at least one modulation analysis, which shows particular advantages in the distinction between interfering and useful signals.
  • it can be determined by the modulation analysis whether and to what extent speech or other signals such as music or interference signals are present in the input signals.
  • EP 1 359 787 A2 a fitting method based on a signal-to-noise ratio.
  • acoustic categories such as speech, car noise, music, etc. are individually trained.
  • the object of the present invention is therefore to improve speech understanding in a noisy environment for users of hearing devices and in particular of hearing aids.
  • this object is achieved by an adaptation method for adapting a hearing device to a user by recording a speech signal of a given speaker, analyzing the speech signal with provision of a corresponding speaker-specific analysis result and setting an algorithm for reducing noise the hearing device as a function of the speaker-specific analysis result.
  • an adaptation device for adapting a hearing device to a user with a sound providing device for providing a speaker-specific speech signal of a given speaker, an analysis device for analyzing the speech signal and a transmission device for transmitting the speaker-specific analysis result of the analysis device to the hearing device.
  • a preferred sound i. H. the speech signal of the desired speaker are analyzed in detail, so that the features of the speech signal can be used to control the hearing device.
  • a preferred sound i. H. the speech signal of the desired speaker are analyzed in detail, so that the features of the speech signal can be used to control the hearing device.
  • the analysis result from analyzing the speech signal comprises an amplitude distribution, a long-term spectrum, a bandwidth and / or a modulation value. These features can be used to emphasize the language of the desired speaker accordingly.
  • interference signals can be more selectively reduced during operation of the hearing device.
  • the speech signal can be emphasized over other noise.
  • a noise algorithm can be implemented which uses the amplitude distribution of the speech signal (eg Ephraim-Malah method).
  • the analysis result comprises an amplitude distribution of the speech signal and this amplitude distribution is utilized for the noise suppression algorithm. This makes it possible to significantly improve the SNR ratio, especially with speech.
  • the basic idea of the present invention is to make specific knowledge about the speech signal of the speaker available for listening situations with a known speaker of the hearing device or the hearing device in a kind of training phase.
  • This specific knowledge includes physical characteristics of the speech of the known speaker. Typical features that characterize speech signals are the long-term spectrum, the bandwidth, the amplitude distribution, the modulation, and the like.
  • the speech of the target speaker is first recorded in a quiet environment in the inventive fitting process according to step S1.
  • a recording of about 1 min is sufficient. Length. It is important to record the speech in a sufficiently quiet environment, so that the analysis is as undisturbed as possible.
  • the hearing aid wearer will bring his life partner to the fitting session in order to have his speech signals recorded. Alternatively, he may also, for example, bring a recording of the voice of the life partner or the desired person for adaptation.
  • a second step S2 of the fitting process the analysis of the recorded speech signal now takes place.
  • these features can be, for example, the long-term spectrum, the bandwidth, the amplitude distribution or the modulation. All of this information is usually characteristic of the language of an individual person. However, the more information that can be obtained about the language, the better a corresponding speech signal can be recognized for further processing.
  • step S3 From the information about the speech signal obtained in step S2, parameters for a noise reduction algorithm are calculated in step S3. In this way, an individual configuration of the noise reduction algorithm can still be found during the fitting process.
  • step S3 the configuration of the noise algorithm determined in step S3 is transmitted to the hearing aid, as shown in FIG. 2 is shown with the dashed arrow.
  • the hearing aid is shown schematically with some function blocks.
  • the microphone 10 symbolizes the signal input.
  • the handset 11 indicates the signal output of the hearing aid.
  • signal processing components such as the noise reduction algorithm 12. This ensures that the signal of the microphone 10 can be freed of noise and thus forwarded to an amplifier 13.
  • the amplifier 13 in turn supplies a hearing aid output signal to the handset 11.
  • the noise reduction algorithm 12 may be operated with a standard configuration stored in a first memory 14.
  • a second memory 15 an individual configuration is stored containing parameters obtained from the fitting process.
  • the individual configuration includes the individual features obtained from the speech signal of the desired speaker in step S2 of the fitting process and the parameters calculated from those features in step S3 .
  • the noise reduction then takes place on the basis of both the standard configuration and the individual configuration. With the individually configured noise algorithm, a better extraction of the speech signal can be achieved.
  • Step S2 the individual configuration would involve the blocks “error estimation”, “weighting formula” and “post-processing”.
  • the weighting formula of the Ephraim-Malah method specifically requires the amplitude distribution of the useful signal, where otherwise a Gaussian distribution is generally assumed. Therefore, in the in FIG. 2 Step S2 shown for the specific preferred speaker a-priori in the training phase determines the individual amplitude distribution. With the amplitude statistical features of the language of the desired speaker, the speech signal of this speaker can then be amplified output in the hearing aid with an improved SNR ratio.
  • the noise reduction parameters relating to the speech signal obtained in the fitting process may also be used to discriminate the speech of the known speaker and to suppress as much as possible a corresponding speech signal.

Landscapes

  • Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Acoustics & Sound (AREA)
  • Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Otolaryngology (AREA)
  • Neurosurgery (AREA)
  • General Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Quality & Reliability (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Circuit For Audible Band Transducer (AREA)
EP07121483A 2006-11-27 2007-11-26 Adaptation d'un dispositif auditif à un signal vocal Ceased EP1926087A1 (fr)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
DE102006055935 2006-11-27

Publications (1)

Publication Number Publication Date
EP1926087A1 true EP1926087A1 (fr) 2008-05-28

Family

ID=38951927

Family Applications (1)

Application Number Title Priority Date Filing Date
EP07121483A Ceased EP1926087A1 (fr) 2006-11-27 2007-11-26 Adaptation d'un dispositif auditif à un signal vocal

Country Status (2)

Country Link
US (1) US20080175423A1 (fr)
EP (1) EP1926087A1 (fr)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8462969B2 (en) * 2010-04-22 2013-06-11 Siemens Audiologische Technik Gmbh Systems and methods for own voice recognition with adaptations for noise robustness
EP2528356A1 (fr) * 2011-05-25 2012-11-28 Oticon A/s Stratégie de compensation dépendant de la parole
US9508343B2 (en) * 2014-05-27 2016-11-29 International Business Machines Corporation Voice focus enabled by predetermined triggers
EP3343951A1 (fr) 2016-12-27 2018-07-04 GN Hearing A/S Modélisation de signal sonore sur la base de son d'objet enregistré
US10212503B1 (en) 2017-08-09 2019-02-19 Gn Hearing A/S Acoustic device

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0886263A2 (fr) * 1997-06-16 1998-12-23 Digital Equipment Corporation Traitement de la parole adapté aux bruits environmentaux
DE10114101A1 (de) 2001-03-22 2002-06-06 Siemens Audiologische Technik Verfahren zum Verarbeiten eines Eingangssignals in einer Signalverarbeitungseinheit eines Hörgerätes sowie Schaltung zur Durchführung des Verfahrens
EP1359787A2 (fr) 2002-04-25 2003-11-05 GN ReSound as Méthode d'adaptation et prothèse auditive basées sur les données de perte du rapport signal-bruit

Family Cites Families (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4628529A (en) * 1985-07-01 1986-12-09 Motorola, Inc. Noise suppression system
US4630304A (en) * 1985-07-01 1986-12-16 Motorola, Inc. Automatic background noise estimator for a noise suppression system
US4630302A (en) * 1985-08-02 1986-12-16 Acousis Company Hearing aid method and apparatus
FI108830B (fi) * 1993-12-23 2002-03-28 Nokia Corp Menetelmä ja laite kaiun vaimentamiseksi puhelinlaitteessa
US5771299A (en) * 1996-06-20 1998-06-23 Audiologic, Inc. Spectral transposition of a digital audio signal
US7676372B1 (en) * 1999-02-16 2010-03-09 Yugen Kaisha Gm&M Prosthetic hearing device that transforms a detected speech into a speech of a speech form assistive in understanding the semantic meaning in the detected speech
WO2001020965A2 (fr) * 2001-01-05 2001-03-29 Phonak Ag Procede de determination d'une situation d'environnement acoustique momentanee, utilisation de ce procede, et prothese auditive
US20020150264A1 (en) * 2001-04-11 2002-10-17 Silvia Allegro Method for eliminating spurious signal components in an input signal of an auditory system, application of the method, and a hearing aid
US6728385B2 (en) * 2002-02-28 2004-04-27 Nacre As Voice detection and discrimination apparatus and method
US7218741B2 (en) * 2002-06-05 2007-05-15 Siemens Medical Solutions Usa, Inc System and method for adaptive multi-sensor arrays
DK1453356T3 (da) * 2003-02-27 2013-02-11 Siemens Audiologische Technik Fremgangsmåde til indstilling af et høresystem og et tilsvarende høresystem
JP3836815B2 (ja) * 2003-05-21 2006-10-25 インターナショナル・ビジネス・マシーンズ・コーポレーション 音声認識装置、音声認識方法、該音声認識方法をコンピュータに対して実行させるためのコンピュータ実行可能なプログラムおよび記憶媒体
US20040252855A1 (en) * 2003-06-16 2004-12-16 Remir Vasserman Hearing aid
DE10327889B3 (de) * 2003-06-20 2004-09-16 Siemens Audiologische Technik Gmbh Verfahren zum Betrieb eines Hörhilfegerätes sowie Hörhilfegerät mit einem Mikrofonsystem, bei dem unterschiedliche Richtcharakteristiken einstellbar sind und Programmiergerät dafür
DE102004017486A1 (de) * 2004-04-08 2005-10-27 Siemens Ag Verfahren zur Geräuschreduktion bei einem Sprach-Eingangssignal
DE102005012983A1 (de) * 2005-03-21 2006-09-28 Siemens Audiologische Technik Gmbh Hörgerät mit sprachspezifischer Einstellung und entsprechendes Verfahren
DE102005032274B4 (de) * 2005-07-11 2007-05-10 Siemens Audiologische Technik Gmbh Hörvorrichtung und entsprechendes Verfahren zur Eigenstimmendetektion
JP4359599B2 (ja) * 2006-02-28 2009-11-04 リオン株式会社 補聴器
US20070282392A1 (en) * 2006-05-30 2007-12-06 Phonak Ag Method and system for providing hearing assistance to a user
US8005246B2 (en) * 2007-10-23 2011-08-23 Swat/Acr Portfolio Llc Hearing aid apparatus

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0886263A2 (fr) * 1997-06-16 1998-12-23 Digital Equipment Corporation Traitement de la parole adapté aux bruits environmentaux
DE10114101A1 (de) 2001-03-22 2002-06-06 Siemens Audiologische Technik Verfahren zum Verarbeiten eines Eingangssignals in einer Signalverarbeitungseinheit eines Hörgerätes sowie Schaltung zur Durchführung des Verfahrens
EP1359787A2 (fr) 2002-04-25 2003-11-05 GN ReSound as Méthode d'adaptation et prothèse auditive basées sur les données de perte du rapport signal-bruit

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
EPHRAIM Y. AND MALAH D.: "Speech enhancement using a minimum mean-square error short-time spectral amplitude estimator", IEEE TRANS. A-COUST, SPEECH, SIGNAL PROCESSING, vol. 32, no. 5, 1984, pages 1109 - 1121
J.L.FLANAGAN: "Speech Analysis Synthesis and Perception", 1972, SPRINGER-VERLAG, BERLIN, HEIDELBERG, NEW YORK, XP002466026 *
LOTTER TH.: "Single and multimicrophone speech enhancement for hearing aids", VERLAG MAINZ, 2004, AACHEN
MARK MARZINZIK: "Noise Reduction Schemes for Digital Hearing Aids and their Use for the Hearing Impaired", 19 December 2000, UNIVERSITÄT OLDENBURG, OLDENBURG, XP002466027 *

Also Published As

Publication number Publication date
US20080175423A1 (en) 2008-07-24

Similar Documents

Publication Publication Date Title
EP3451705B1 (fr) Procédé et dispositif de reconnaissance rapide de voix propre
EP2603018B1 (fr) Dispositif auditif avec détection d'activité de locuteur et procédé de fonctionnement d'un dispositif auditif
EP2180726A1 (fr) Localisation du son avec des prothèses auditives binauriculaires
EP3386215B1 (fr) Procédé de fonctionnement d'un dispositif d'aide auditive et dispositif d'aide auditive
DE102008031150B3 (de) Verfahren zur Störgeräuschunterdrückung und zugehöriges Hörgerät
EP3873108A1 (fr) Système auditif pourvu d'au moins un instrument auditif porté dans ou sur l'oreille de l'utilisateur, ainsi que procédé de fonctionnement d'un tel système auditif
DE102010012622A1 (de) Binaurales Verfahren und binaurale Anordnung zur Sprachsteuerung von Hörgeräten
EP1926087A1 (fr) Adaptation d'un dispositif auditif à un signal vocal
DE102007035171A1 (de) Verfahren zum Anpassen eines Hörgeräts mit Hilfe eines perzeptiven Modells
EP2495724B1 (fr) Procédé et dispositif destinés à l'évaluation d'un bruit parasite
DE102007035174A1 (de) Hörvorrichtung gesteuert durch ein perzeptives Modell und entsprechendes Verfahren
EP2109329A2 (fr) Procédé d'évaluation en plusieurs étapes destiné à la réduction des bruits parasites et dispositif auditif
EP3585073A1 (fr) Procédé de commande de la transmission de données entre au moins un appareil auditif et un périphérique d'un système d'appareil auditif ainsi que système d'appareil auditif associé
US8385572B2 (en) Method for reducing noise using trainable models
EP2434781A1 (fr) Procédé de reconstruction d'un signal vocal et dispositif auditif
EP1962554A2 (fr) Appareil auditif doté d'une séparation de signal d'erreur et procédé correspondant
DE10142347C1 (de) Automatische Adaption von Hörgeräten an unterschiedliche Hörsituationen
EP2982136B1 (fr) Procédé d'estimation d'un signal utile et dispositif auditif
EP1909535B1 (fr) Appareil auditif avec canaux d'entrée controlés et procédé correspondant
EP3985997B1 (fr) Système d'appareil auditif et son procédé de fonctionnement
DE102020201615B3 (de) Hörsystem mit mindestens einem im oder am Ohr des Nutzers getragenen Hörinstrument sowie Verfahren zum Betrieb eines solchen Hörsystems
WO2012019636A1 (fr) Procédé permettant de faire fonctionner un appareil auditif et appareil auditif correspondant
EP3048813A1 (fr) Procédé et dispositif de suppression du bruit basée sur l'inter-corrélation de bandes secondaires
WO2014049455A1 (fr) Système auditif ainsi que procédé de transmission
DE102008063207A1 (de) Verfahren zum Betreiben einer Hörvorrichtung mit Sprachsynthese und Hörvorrichtung

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IS IT LI LT LU LV MC MT NL PL PT RO SE SI SK TR

AX Request for extension of the european patent

Extension state: AL BA HR MK RS

17P Request for examination filed

Effective date: 20080804

17Q First examination report despatched

Effective date: 20080908

AKX Designation fees paid

Designated state(s): AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IS IT LI LT LU LV MC MT NL PL PT RO SE SI SK TR

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE APPLICATION HAS BEEN REFUSED

18R Application refused

Effective date: 20100501