TR201917042A2 - Yeni bir metot ile sinyal enerji hesabı ve bu metotla elde edilen konuşma sinyali kodlayıcı. - Google Patents

Yeni bir metot ile sinyal enerji hesabı ve bu metotla elde edilen konuşma sinyali kodlayıcı. Download PDF

Info

Publication number
TR201917042A2
TR201917042A2 TR2019/17042A TR201917042A TR201917042A2 TR 201917042 A2 TR201917042 A2 TR 201917042A2 TR 2019/17042 A TR2019/17042 A TR 2019/17042A TR 201917042 A TR201917042 A TR 201917042A TR 201917042 A2 TR201917042 A2 TR 201917042A2
Authority
TR
Turkey
Prior art keywords
signal
energy
regions
signals
speech
Prior art date
Application number
TR2019/17042A
Other languages
English (en)
Inventor
Özaydin Selma
Original Assignee
Cankaya Ueniversitesi
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 Cankaya Ueniversitesi filed Critical Cankaya Ueniversitesi
Priority to TR2019/17042A priority Critical patent/TR201917042A2/tr
Priority to PCT/TR2020/050787 priority patent/WO2021091504A1/en
Priority to US17/767,953 priority patent/US20240105213A1/en
Publication of TR201917042A2 publication Critical patent/TR201917042A2/tr

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
    • 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
    • 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
    • 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
    • G10L25/45—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of analysis window
    • 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
    • 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
    • G10L2025/783—Detection of presence or absence of voice signals based on threshold decision
    • G10L2025/786—Adaptive threshold
    • 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
    • G10L25/93—Discriminating between voiced and unvoiced parts of speech signals

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)

Abstract

Buluş, sinyallerin kodlanmasında yeni bir metot önerisi sinyallerin kodlanmasını, kodlanmış sinyaller ile enerji hesabı yapılmasını ve bu kodlanmış sinyalin enerji bölgeleri üzerinden konuşma sinyalindeki konuşma aktivite bölgelerinin belirlenmesini sağlayan sinyal kodlayıcı ve yöntemi ile ilgilidir. Buluş özellikle, gürültülü giriş sinyallerinin önerilen metotla kodlanmasını, kodlanmış sinyallerin enerji bölgelerinin yeni bir metotla hesaplanmasını, bu sayede yüksek gürültülü koşullarda dahi bir enerji sinyali ortaya konulmasını ve önerilen enerji hesaplaması kullanılarak bir giriş konuşma sinyalinin konuşma aktivite bölgelerinin (KAB) tespiti işleminde, konuşma olan ve sessiz bölgelerin ayrımı yapılmasını sağlayan sinyal kodlayıcı ve yöntemi ile ilgilidir.
TR2019/17042A 2019-11-04 2019-11-04 Yeni bir metot ile sinyal enerji hesabı ve bu metotla elde edilen konuşma sinyali kodlayıcı. TR201917042A2 (tr)

Priority Applications (3)

Application Number Priority Date Filing Date Title
TR2019/17042A TR201917042A2 (tr) 2019-11-04 2019-11-04 Yeni bir metot ile sinyal enerji hesabı ve bu metotla elde edilen konuşma sinyali kodlayıcı.
PCT/TR2020/050787 WO2021091504A1 (en) 2019-11-04 2020-08-31 Signal energy calculation with a new method and a speech signal encoder obtained by means of this method
US17/767,953 US20240105213A1 (en) 2019-11-04 2020-08-31 Signal energy calculation with a new method and a speech signal encoder obtained by means of this method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
TR2019/17042A TR201917042A2 (tr) 2019-11-04 2019-11-04 Yeni bir metot ile sinyal enerji hesabı ve bu metotla elde edilen konuşma sinyali kodlayıcı.

Publications (1)

Publication Number Publication Date
TR201917042A2 true TR201917042A2 (tr) 2021-05-21

Family

ID=75849022

Family Applications (1)

Application Number Title Priority Date Filing Date
TR2019/17042A TR201917042A2 (tr) 2019-11-04 2019-11-04 Yeni bir metot ile sinyal enerji hesabı ve bu metotla elde edilen konuşma sinyali kodlayıcı.

Country Status (3)

Country Link
US (1) US20240105213A1 (tr)
TR (1) TR201917042A2 (tr)
WO (1) WO2021091504A1 (tr)

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH03114100A (ja) * 1989-09-28 1991-05-15 Matsushita Electric Ind Co Ltd 音声区間検出装置
JP3673507B2 (ja) * 2002-05-16 2005-07-20 独立行政法人科学技術振興機構 音声波形の特徴を高い信頼性で示す部分を決定するための装置およびプログラム、音声信号の特徴を高い信頼性で示す部分を決定するための装置およびプログラム、ならびに擬似音節核抽出装置およびプログラム
JP4521673B2 (ja) * 2003-06-19 2010-08-11 株式会社国際電気通信基礎技術研究所 発話区間検出装置、コンピュータプログラム及びコンピュータ
JP5229234B2 (ja) * 2007-12-18 2013-07-03 富士通株式会社 非音声区間検出方法及び非音声区間検出装置

Also Published As

Publication number Publication date
US20240105213A1 (en) 2024-03-28
WO2021091504A1 (en) 2021-05-14

Similar Documents

Publication Publication Date Title
DE602008002902D1 (de) Eingebettete komprimierung für ruhe- und hintergrundrauschen
MX2017011493A (es) Codificador de audio para la codificación de una señal de múltiples canales y un decodificador de audio para la decodificación de una señal de audio codificada.
NO20075511L (no) Splittbandkoding av talesignaler
RU2011145865A (ru) Транскодировщик аудиоформата
MY183019A (en) Determining weighting functions for line spectral frequency coefficients
DE602005002833D1 (de) Kompensation von multikanal-audio energieverlusten
TR201908029T4 (tr) Ses kodlama ve kod çözmede faz bilgisinin etkili kullanımı.
JP6629834B2 (ja) ハーモニックフィルタツールのハーモニック依存制御
MX2017001235A (es) Codificador y decodificador de audio usando un procesador de dominio de frecuencia con un relleno de intervalo de banda completa y un procesador de dominio de tiempo.
GB2532379A (en) Wind noise reduction
MY178697A (en) Encoder, decoder and methods for signal-dependent zoom-transform in spatial audio object coding
WO2009050896A1 (ja) ストリーム合成装置、復号装置、方法
KR20120089335A (ko) 매개변수 인코딩 및 디코딩
ATE542217T1 (de) Informationssignalcodierung
MY164393A (en) Mdct-based complex prediction stereo coding
DK1825461T3 (da) Fremgangsmåde og indretning til kunstig udvidelse af båndbredden af talesignaler
MY178306A (en) Low-frequency emphasis for lpc-based coding in frequency domain
ATE518224T1 (de) Audiokodierer und -dekodierer
MX356164B (es) Codificador para codificar una señal de audio, sistema de audio de transmisión y método para determinar valores de corrección.
NZ721890A (en) Harmonic bandwidth extension of audio signals
RU2013146688A (ru) Устройство и способ для выполнения кодирования методом хаффмана
MX350690B (es) Método y descodificador para un concepto paramétrico de codificación de objeto de audio espacial generalizado para casos de mezcla descendente/mezcla ascendente de multicanal.
WO2009096715A3 (ko) 오디오 신호의 부호화, 복호화 방법 및 장치
MX2016004923A (es) Concepto para codificar una señal de audio y decodificar una señal de audio usando informacion de conformacion espectral relacionada con la voz.
MY190424A (en) Audio encoder for encoding an audio signal, method for encoding an audio signal and computer program under consideration of a detected peak spectral region in an upper frequency band