EP0161423A1 - Procédé pour déterminer les limites d'un signal mélangé à du bruit de fond - Google Patents

Procédé pour déterminer les limites d'un signal mélangé à du bruit de fond Download PDF

Info

Publication number
EP0161423A1
EP0161423A1 EP85103259A EP85103259A EP0161423A1 EP 0161423 A1 EP0161423 A1 EP 0161423A1 EP 85103259 A EP85103259 A EP 85103259A EP 85103259 A EP85103259 A EP 85103259A EP 0161423 A1 EP0161423 A1 EP 0161423A1
Authority
EP
European Patent Office
Prior art keywords
signal
variable
interest
determined
input variable
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.)
Granted
Application number
EP85103259A
Other languages
German (de)
English (en)
Other versions
EP0161423B1 (fr
Inventor
Berhard Dipl.-Ing. Kämmerer
Ulrich Dipl.-Ing. Müller
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.)
Siemens AG
Original Assignee
Siemens AG
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 AG filed Critical Siemens AG
Priority to AT85103259T priority Critical patent/ATE40235T1/de
Publication of EP0161423A1 publication Critical patent/EP0161423A1/fr
Application granted granted Critical
Publication of EP0161423B1 publication Critical patent/EP0161423B1/fr
Expired 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
    • 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
    • G10L25/87—Detection of discrete points within a voice signal

Definitions

  • the present invention relates to a method for detecting the limits of signals which occur in front of a background signal mixture, in particular signal limits for the speech processing of words spoken in front of a background noise, the amplitude behavior of which is used as a distinguishing criterion between a signal of interest and the background signal or background signal mixture.
  • the present invention has for its object to provide a method of the type mentioned, which can be carried out inexpensively, in terms of both hardware and software, but relatively works accurately and remains unaffected by certain irrelevant signal disturbances (for example the sound of a banging door, street noise, the voices of a large number of people, etc.)
  • the method according to the present invention uses their amplitude behavior as a distinguishing criterion between a signal of interest and the background signal or background signal mixture.
  • a recorded and subsequently preprocessed signal or signal mixture namely an input variable E
  • E a recorded and subsequently preprocessed signal or signal mixture
  • R reference quantity
  • dN fluctuation range
  • the recorded signal or signal mixture Z (t) is first amplified, then filtered by means of a bandpass filter and then subjected to an analog / digital conversion, which results in the input variable E mentioned, see FIG. 1.
  • the variables obtained in this way become Auxiliary variables S1, N2 derived, compare FIG. 3.
  • the current frequency of passage N1 is determined in relation to the reference variable R.
  • one of the previously derived auxiliary variables S1 or S2 is assigned to an evaluation variable S.
  • the current input variable E is measured on the basis of this evaluation variable S.
  • an operation 01 which is dependent on the position of the input variable E relative to the evaluation variable S is carried out.
  • Two limit values UG, OG1 are defined on the basis of the type of signal of interest. The result of operation 01 is limited by the first limit.
  • the second, upper limit value OG1 is reached, the presence of a signal of interest is recognized.
  • the exact beginning of the signal SB is a defined time period before the relevant detection time ZE1, see FIG. 4 and FIG. 5.
  • a third step the position of the input variable E relative to the evaluation variable S is evaluated by a further operation 02 in such a way that when a second limit value OG2 predetermined based on the type of the signal of interest is reached, the absence of the signal of interest detected in the second step is present is detected.
  • the exact end of signal SE is a defined time period before the relevant detection time ZE2, see FIG. 6 and FIG. 7.
  • said operation 01 is provided as an integration process.
  • the exact start of the signal SB is due to the temporal position of the last value of the integration result equal to the lower limit UG before the relevant detection time ZE1.
  • the first step can advantageously be repeated in the event that the input variable E exceeds a threshold adapted to the background signal mixture.
  • a waiting period is expediently inserted between the first step and the second step.
  • the evaluation variable S is defined as follows:
  • the first operation is defined as follows:
  • the second operation is defined as follows:
  • processing and evaluation processes according to the invention can be carried out by means of digital circuits, but are expediently by means of a Microprocessor and corresponding programs for it.
  • FIG. 2 shows a flow chart for a word boundary detection.
  • the steps mentioned, namely the first step, the second step and the third step, are illustrated again clearly in this flowchart.
  • Figure 8 shows, as already explained at the outset, a diagram for an entire word boundary recognition of the spoken word "stop”, with in the upper part of the diagram a waveform of the relevant time signal with assigned upper and lower threshold values, and the middle part of the diagram a generated digital display signal for the State "word of interest is present" and the process of word start and word end recognition is shown in the lower part of the diagram.
  • the environmental noise will have dominant frequency components in the area of the vowel formants.
  • these formants mostly have relatively large amplitudes, so that they can also be detected at a high threshold.
  • the method according to the invention is of course not limited to the exemplary embodiments described.
  • it can also be used for monitoring purposes to find certain typical signal profiles within a signal mixture, for example for radio monitoring purposes.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computational Linguistics (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)
  • Complex Calculations (AREA)
  • Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
  • Optical Radar Systems And Details Thereof (AREA)
  • Stereo-Broadcasting Methods (AREA)
EP85103259A 1984-03-28 1985-03-20 Procédé pour déterminer les limites d'un signal mélangé à du bruit de fond Expired EP0161423B1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
AT85103259T ATE40235T1 (de) 1984-03-28 1985-03-20 Verfahren zur erfassung der grenzen von signalen, die vor einem hintergrundsignalgemisch auftreten.

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
DE3411485 1984-03-28
DE19843411485 DE3411485A1 (de) 1984-03-28 1984-03-28 Verfahren zur erfassung der grenzen von signalen, die vor einem hintergrundsignalgemisch auftreten

Publications (2)

Publication Number Publication Date
EP0161423A1 true EP0161423A1 (fr) 1985-11-21
EP0161423B1 EP0161423B1 (fr) 1989-01-18

Family

ID=6231908

Family Applications (1)

Application Number Title Priority Date Filing Date
EP85103259A Expired EP0161423B1 (fr) 1984-03-28 1985-03-20 Procédé pour déterminer les limites d'un signal mélangé à du bruit de fond

Country Status (4)

Country Link
EP (1) EP0161423B1 (fr)
JP (1) JPS60218700A (fr)
AT (1) ATE40235T1 (fr)
DE (2) DE3411485A1 (fr)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0275099A2 (fr) * 1987-01-16 1988-07-20 Sharp Kabushiki Kaisha Dispositif d'analyse et de synthèse de la parole
CN115019834A (zh) * 2022-05-23 2022-09-06 北京声智科技有限公司 语音端点的检测方法、装置、电子设备、存储介质及产品

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
FR2304135A1 (fr) * 1975-03-10 1976-10-08 Threshold Tech Detecteur de limites de mots pour equipement d'identification de parole

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE1772633U (de) 1958-06-26 1958-08-21 No Sag Drahtfedern Gmbh Federkoerper fuer polsterrahmen.
GB1012765A (en) 1964-03-06 1965-12-08 Standard Telephones Cables Ltd Apparatus for the analysis of waveforms
GB1495389A (en) 1974-01-31 1977-12-14 Atomic Energy Authority Uk Apparatus for providing time reference signals
FR2402971A1 (fr) 1977-09-09 1979-04-06 Onera (Off Nat Aerospatiale) Extracteur syntactique de signaux evolutifs et procede d'extraction
DE3003556C2 (de) 1980-02-01 1984-12-06 Dornier Gmbh, 7990 Friedrichshafen Verfahren und Vorrichtung zur Bestimmung eines Nutzsignals aus einem mit Störsignalen überlagerten bandbegrenzten Signal
US4388495A (en) 1981-05-01 1983-06-14 Interstate Electronics Corporation Speech recognition microcomputer
DE3207556C2 (de) 1982-03-03 1983-12-22 Vierling, Oskar, Prof. Dr.Phil.Habil., 8553 Ebermannstadt Anordnung zum Messen der charakteristischen Zeiten von Impulsen und Impulsserien

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
FR2304135A1 (fr) * 1975-03-10 1976-10-08 Threshold Tech Detecteur de limites de mots pour equipement d'identification de parole

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
ICASSP 83, PROCEEDINGS OF THE IEEE INTERNATIONAL CONFERENCE ON ACOUTICS, SPEECH AND SIGNAL PROCESSING, 14.-16. April 1983, Boston, Massachusetts, Band 3, Seiten 1156-1159, IEEE, New York, US; G. NEBEN u.a.: "Experiments in isolated word recognition using noisy speech" *
IEEE TRANSACTIONS ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, Band ASSP-29, Nr. 4, August 1981, Seiten 777-785, IEEE, New York, US; L.F. LAMEL u.a.: "An improved endpoint detector for isolated word recognition" *
IEEE TRANSACTIONS ON COMMUNICATIONS, Band COM-30, Nr. 4, April 1982, Seiten 739-750, IEEE, New York, US; Y. YATSUZUKA: "Highly sensitive speech detector and high-speed voiceband data discriminator in DSI-ADPCM systems" *
THE BELL SYSTEM TECHNICAL JOURNAL, Band 54, Nr. 2, Februar 1975, Seiten 297-315, American Telephone and Telegraph Co., New York, US; L.R. RABINER u.a.: "An algorithm for determining the endpoints of isolated utterances" *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0275099A2 (fr) * 1987-01-16 1988-07-20 Sharp Kabushiki Kaisha Dispositif d'analyse et de synthèse de la parole
EP0275099A3 (en) * 1987-01-16 1990-09-19 Sharp Kabushiki Kaisha Voice analyzing and synthesizing apparatus
CN115019834A (zh) * 2022-05-23 2022-09-06 北京声智科技有限公司 语音端点的检测方法、装置、电子设备、存储介质及产品

Also Published As

Publication number Publication date
JPS60218700A (ja) 1985-11-01
DE3411485A1 (de) 1985-10-03
EP0161423B1 (fr) 1989-01-18
ATE40235T1 (de) 1989-02-15
DE3567757D1 (en) 1989-02-23

Similar Documents

Publication Publication Date Title
DE69926851T2 (de) Verfahren und Vorrichtung zur Sprachaktivitätsdetektion
DE3752288T2 (de) Sprachprozessor
EP0076233B1 (fr) Procédé et dispositif pour traitement digital de la parole réduisant la redondance
DE69605559T2 (de) Glasbruchdetektor
DE69918635T2 (de) Vorrichtung und Verfahren zur Sprachverarbeitung
EP0110467B2 (fr) Dispositif pour la détection des silences dans les signaux de paroles
DE3422877C2 (fr)
EP1101390B1 (fr) Appareil auditif permettant une meilleure comprehension de la parole grace a un traitement de signal selectif en frequence, et procede permettant de faire fonctionner un tel appareil auditif
DE69922769T2 (de) Vorrichtung und Verfahren zur Sprachverarbeitung
DE3102385C2 (fr)
EP2031581A1 (fr) Procédé destiné à la reconnaissance d'un évènement acoustique dans un signal audio
DE69132148T2 (de) Vorrichtung zur Verarbeitung eines Signals
DE2021126B2 (de) Spracherkennungsanordnung
EP1382034B1 (fr) Procede de determination de valeurs caracteristiques d'intensite de bruits de fond dans des pauses de voix de signaux vocaux
EP0161423B1 (fr) Procédé pour déterminer les limites d'un signal mélangé à du bruit de fond
EP0775348B1 (fr) Procede de detection de signaux par classification en logique floue
EP2159601A2 (fr) Procédé de fixation d'un arbre de réception, dispositif de fixation d'un arbre de réception, sonar à ultrasons
DE68919924T2 (de) Verfahren zur Feststellung des Sättigungspegels eines Sprachsignals.
EP1005016A2 (fr) Procédé et dispositif de circuit pour mesurer le niveau de parole dans un système de traitement du signal de parole
DE60315522T2 (de) Klickgeräusch-erkennung in einem digitalen audiosignal
DE2915834A1 (de) Vorrichtung zum ueberwachen des betriebsverhaltens eines senders
DE1772633A1 (de) Verfahren zur Spracherkennung
DE2649259C2 (de) Verfahren zum automatischen Erkennen von gestörter Telefonsprache
DE10209340A1 (de) Verfahren zur Auswertung von Spektrogrammen oder Chromatogrammen sowie ein Analysesystem und eine Auswerteelektronik zur Ausführung des Verfahrens
DE19854420C2 (de) Verfahren und Einrichtung zum Verarbeiten von Schallsignalen

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

17P Request for examination filed

Effective date: 19850827

AK Designated contracting states

Designated state(s): AT CH DE FR GB IT LI

17Q First examination report despatched

Effective date: 19870803

GRAA (expected) grant

Free format text: ORIGINAL CODE: 0009210

AK Designated contracting states

Kind code of ref document: B1

Designated state(s): AT CH DE FR GB IT LI

REF Corresponds to:

Ref document number: 40235

Country of ref document: AT

Date of ref document: 19890215

Kind code of ref document: T

REF Corresponds to:

Ref document number: 3567757

Country of ref document: DE

Date of ref document: 19890223

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: AT

Payment date: 19890224

Year of fee payment: 5

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: GB

Payment date: 19890228

Year of fee payment: 5

ET Fr: translation filed
PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: FR

Payment date: 19890322

Year of fee payment: 5

ITTA It: last paid annual fee
ITF It: translation for a ep patent filed
GBT Gb: translation of ep patent filed (gb section 77(6)(a)/1977)
PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: DE

Payment date: 19890529

Year of fee payment: 5

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: CH

Payment date: 19890623

Year of fee payment: 5

PLBE No opposition filed within time limit

Free format text: ORIGINAL CODE: 0009261

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

Free format text: STATUS: NO OPPOSITION FILED WITHIN TIME LIMIT

26N No opposition filed
PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: GB

Effective date: 19900320

Ref country code: AT

Effective date: 19900320

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: LI

Effective date: 19900331

Ref country code: CH

Effective date: 19900331

GBPC Gb: european patent ceased through non-payment of renewal fee
PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: FR

Effective date: 19901130

REG Reference to a national code

Ref country code: CH

Ref legal event code: PL

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: DE

Effective date: 19901201

REG Reference to a national code

Ref country code: FR

Ref legal event code: ST