SlideShare a Scribd company logo
1 of 8
Download to read offline
Speaker verification
using Oguma histogram


  S117036   Ami Inoamta

  Supervisor:M.Sugiyama
Outline
●   Background
●   Oguma histogram
●   Speaker verification algorithm
●   Speech analysis condition
●   Learn histogram , Verification histogram
●   Result of speaker verification
Background
●   Diffusion of smartphone.
●   Security is more important.
    →Speaker verification system

●   VQ : most popular. But calculation amount is large.
●   Oguma histogram : calculation amount is small.
    →smartphone application.


●   First, test this performance in PC terminal.
Oguma histogram
                  ●   Do not use VQ.
                  ●   Directly make histogram
                      from feature vectors.
                      1. Set out threshold in each
                      dimension of feature
                      vectors.
                      2. Compare
                      →Space division
                      3.Set out Region ID .
Speaker verification algorithm
Speech analysis condition
        Database                   TIMIT
     Dialect region             New England
       Head count                10 person
 Learning , verification   5 sentence , 5 sentence
    Recording format                wav
     Sampling rate                 16 kHz
Dimension number of MFCC             16
   Filter bank channel               24
      Window size                  16 ms
      Frame shift               8 ms, 16 ms
  Dimension number of       16, 32, 64, 128, 256
       histogram
Learn histogram,Verification histogram
Result of speaker verification
  Female:                              Male:




            Speaker verification result (frame shift 8ms)

More Related Content

Viewers also liked

media studies house style
media studies house stylemedia studies house style
media studies house styleshadiorr
 
Syllabus etica y responsabilidad social presencial
Syllabus etica y responsabilidad social presencialSyllabus etica y responsabilidad social presencial
Syllabus etica y responsabilidad social presencialMilber Fuentes
 
Las relaciones entre_la_etica_y_la_politica
Las relaciones entre_la_etica_y_la_politicaLas relaciones entre_la_etica_y_la_politica
Las relaciones entre_la_etica_y_la_politicaMilber Fuentes
 
Syllabus etica y formción ciudadana presencial
Syllabus etica y formción ciudadana presencialSyllabus etica y formción ciudadana presencial
Syllabus etica y formción ciudadana presencialMilber Fuentes
 
Zygmunt bauman-trabajo-consumismo-y-nuevos-pobres-libro-completo
Zygmunt bauman-trabajo-consumismo-y-nuevos-pobres-libro-completoZygmunt bauman-trabajo-consumismo-y-nuevos-pobres-libro-completo
Zygmunt bauman-trabajo-consumismo-y-nuevos-pobres-libro-completoMilber Fuentes
 
Razon y dominacion_la_legitimidad_en_web
Razon y dominacion_la_legitimidad_en_webRazon y dominacion_la_legitimidad_en_web
Razon y dominacion_la_legitimidad_en_webMilber Fuentes
 

Viewers also liked (6)

media studies house style
media studies house stylemedia studies house style
media studies house style
 
Syllabus etica y responsabilidad social presencial
Syllabus etica y responsabilidad social presencialSyllabus etica y responsabilidad social presencial
Syllabus etica y responsabilidad social presencial
 
Las relaciones entre_la_etica_y_la_politica
Las relaciones entre_la_etica_y_la_politicaLas relaciones entre_la_etica_y_la_politica
Las relaciones entre_la_etica_y_la_politica
 
Syllabus etica y formción ciudadana presencial
Syllabus etica y formción ciudadana presencialSyllabus etica y formción ciudadana presencial
Syllabus etica y formción ciudadana presencial
 
Zygmunt bauman-trabajo-consumismo-y-nuevos-pobres-libro-completo
Zygmunt bauman-trabajo-consumismo-y-nuevos-pobres-libro-completoZygmunt bauman-trabajo-consumismo-y-nuevos-pobres-libro-completo
Zygmunt bauman-trabajo-consumismo-y-nuevos-pobres-libro-completo
 
Razon y dominacion_la_legitimidad_en_web
Razon y dominacion_la_legitimidad_en_webRazon y dominacion_la_legitimidad_en_web
Razon y dominacion_la_legitimidad_en_web
 

Similar to S1170136 week8

Development of voice password based speaker verification system
Development of voice password based speaker verification systemDevelopment of voice password based speaker verification system
Development of voice password based speaker verification systemniranjan kumar
 
Development of voice password based speaker verification system
Development of voice password based speaker verification systemDevelopment of voice password based speaker verification system
Development of voice password based speaker verification systemniranjan kumar
 
HMM based Automatic Arabic Sign Language Translator using
HMM based Automatic Arabic Sign Language Translator usingHMM based Automatic Arabic Sign Language Translator using
HMM based Automatic Arabic Sign Language Translator usingعمر أمين
 
Information and data security pseudorandom number generation and stream cipher
Information and data security pseudorandom number generation and stream cipherInformation and data security pseudorandom number generation and stream cipher
Information and data security pseudorandom number generation and stream cipherMazin Alwaaly
 
Joint MFCC-and-Vector Quantization based Text-Independent Speaker Recognition...
Joint MFCC-and-Vector Quantization based Text-Independent Speaker Recognition...Joint MFCC-and-Vector Quantization based Text-Independent Speaker Recognition...
Joint MFCC-and-Vector Quantization based Text-Independent Speaker Recognition...Ahmed Ayman
 
Dcase2016 oral presentation - Experiments on DCASE 2016: Acoustic Scene Class...
Dcase2016 oral presentation - Experiments on DCASE 2016: Acoustic Scene Class...Dcase2016 oral presentation - Experiments on DCASE 2016: Acoustic Scene Class...
Dcase2016 oral presentation - Experiments on DCASE 2016: Acoustic Scene Class...Ankit Shah
 
Google and SRI talk September 2016
Google and SRI talk September 2016Google and SRI talk September 2016
Google and SRI talk September 2016Hagai Aronowitz
 
FAUST: Fast Per-Scene Encoding Using Entropy-Based Scene Detection and Machin...
FAUST: Fast Per-Scene Encoding Using Entropy-Based Scene Detection and Machin...FAUST: Fast Per-Scene Encoding Using Entropy-Based Scene Detection and Machin...
FAUST: Fast Per-Scene Encoding Using Entropy-Based Scene Detection and Machin...Alpen-Adria-Universität
 
lesson 2 digital data acquisition and data processing
lesson 2 digital data acquisition and data processinglesson 2 digital data acquisition and data processing
lesson 2 digital data acquisition and data processingMathew John
 
TinyML - 4 speech recognition
TinyML - 4 speech recognition TinyML - 4 speech recognition
TinyML - 4 speech recognition 艾鍗科技
 
Fast and Reliable Estimation Schemes in RFID Systems.ppt
Fast and Reliable Estimation Schemes in RFID Systems.pptFast and Reliable Estimation Schemes in RFID Systems.ppt
Fast and Reliable Estimation Schemes in RFID Systems.pptnovrain1
 
Pin pointpresentation
Pin pointpresentationPin pointpresentation
Pin pointpresentationLevan Huan
 
IJCER (www.ijceronline.com) International Journal of computational Engineerin...
IJCER (www.ijceronline.com) International Journal of computational Engineerin...IJCER (www.ijceronline.com) International Journal of computational Engineerin...
IJCER (www.ijceronline.com) International Journal of computational Engineerin...ijceronline
 
Text independent speaker recognition system
Text independent speaker recognition systemText independent speaker recognition system
Text independent speaker recognition systemDeepesh Lekhak
 
STEGANOGRAPHY BASED ASYMMETRIC KEY CRYPTOSYSTEM USING TRELLIS CODED GENETIC A...
STEGANOGRAPHY BASED ASYMMETRIC KEY CRYPTOSYSTEM USING TRELLIS CODED GENETIC A...STEGANOGRAPHY BASED ASYMMETRIC KEY CRYPTOSYSTEM USING TRELLIS CODED GENETIC A...
STEGANOGRAPHY BASED ASYMMETRIC KEY CRYPTOSYSTEM USING TRELLIS CODED GENETIC A...ijesajournal
 
Slope at Zero Crossings (ZC) of Speech Signal for Multi-Speaker Activity Dete...
Slope at Zero Crossings (ZC) of Speech Signal for Multi-Speaker Activity Dete...Slope at Zero Crossings (ZC) of Speech Signal for Multi-Speaker Activity Dete...
Slope at Zero Crossings (ZC) of Speech Signal for Multi-Speaker Activity Dete...ijcisjournal
 
Encrypted Traffic Mining
Encrypted Traffic MiningEncrypted Traffic Mining
Encrypted Traffic MiningHenry Huang
 
The Case for a Signal Oriented Data Stream Management System
The Case for a Signal Oriented Data Stream Management SystemThe Case for a Signal Oriented Data Stream Management System
The Case for a Signal Oriented Data Stream Management SystemReza Rahimi
 

Similar to S1170136 week8 (20)

Development of voice password based speaker verification system
Development of voice password based speaker verification systemDevelopment of voice password based speaker verification system
Development of voice password based speaker verification system
 
Development of voice password based speaker verification system
Development of voice password based speaker verification systemDevelopment of voice password based speaker verification system
Development of voice password based speaker verification system
 
HMM based Automatic Arabic Sign Language Translator using
HMM based Automatic Arabic Sign Language Translator usingHMM based Automatic Arabic Sign Language Translator using
HMM based Automatic Arabic Sign Language Translator using
 
Information and data security pseudorandom number generation and stream cipher
Information and data security pseudorandom number generation and stream cipherInformation and data security pseudorandom number generation and stream cipher
Information and data security pseudorandom number generation and stream cipher
 
Joint MFCC-and-Vector Quantization based Text-Independent Speaker Recognition...
Joint MFCC-and-Vector Quantization based Text-Independent Speaker Recognition...Joint MFCC-and-Vector Quantization based Text-Independent Speaker Recognition...
Joint MFCC-and-Vector Quantization based Text-Independent Speaker Recognition...
 
Dcase2016 oral presentation - Experiments on DCASE 2016: Acoustic Scene Class...
Dcase2016 oral presentation - Experiments on DCASE 2016: Acoustic Scene Class...Dcase2016 oral presentation - Experiments on DCASE 2016: Acoustic Scene Class...
Dcase2016 oral presentation - Experiments on DCASE 2016: Acoustic Scene Class...
 
Google and SRI talk September 2016
Google and SRI talk September 2016Google and SRI talk September 2016
Google and SRI talk September 2016
 
FAUST: Fast Per-Scene Encoding Using Entropy-Based Scene Detection and Machin...
FAUST: Fast Per-Scene Encoding Using Entropy-Based Scene Detection and Machin...FAUST: Fast Per-Scene Encoding Using Entropy-Based Scene Detection and Machin...
FAUST: Fast Per-Scene Encoding Using Entropy-Based Scene Detection and Machin...
 
lesson 2 digital data acquisition and data processing
lesson 2 digital data acquisition and data processinglesson 2 digital data acquisition and data processing
lesson 2 digital data acquisition and data processing
 
ASR_final
ASR_finalASR_final
ASR_final
 
TinyML - 4 speech recognition
TinyML - 4 speech recognition TinyML - 4 speech recognition
TinyML - 4 speech recognition
 
Fast and Reliable Estimation Schemes in RFID Systems.ppt
Fast and Reliable Estimation Schemes in RFID Systems.pptFast and Reliable Estimation Schemes in RFID Systems.ppt
Fast and Reliable Estimation Schemes in RFID Systems.ppt
 
Pin pointpresentation
Pin pointpresentationPin pointpresentation
Pin pointpresentation
 
IJCER (www.ijceronline.com) International Journal of computational Engineerin...
IJCER (www.ijceronline.com) International Journal of computational Engineerin...IJCER (www.ijceronline.com) International Journal of computational Engineerin...
IJCER (www.ijceronline.com) International Journal of computational Engineerin...
 
Text independent speaker recognition system
Text independent speaker recognition systemText independent speaker recognition system
Text independent speaker recognition system
 
Speaker recognition.
Speaker recognition.Speaker recognition.
Speaker recognition.
 
STEGANOGRAPHY BASED ASYMMETRIC KEY CRYPTOSYSTEM USING TRELLIS CODED GENETIC A...
STEGANOGRAPHY BASED ASYMMETRIC KEY CRYPTOSYSTEM USING TRELLIS CODED GENETIC A...STEGANOGRAPHY BASED ASYMMETRIC KEY CRYPTOSYSTEM USING TRELLIS CODED GENETIC A...
STEGANOGRAPHY BASED ASYMMETRIC KEY CRYPTOSYSTEM USING TRELLIS CODED GENETIC A...
 
Slope at Zero Crossings (ZC) of Speech Signal for Multi-Speaker Activity Dete...
Slope at Zero Crossings (ZC) of Speech Signal for Multi-Speaker Activity Dete...Slope at Zero Crossings (ZC) of Speech Signal for Multi-Speaker Activity Dete...
Slope at Zero Crossings (ZC) of Speech Signal for Multi-Speaker Activity Dete...
 
Encrypted Traffic Mining
Encrypted Traffic MiningEncrypted Traffic Mining
Encrypted Traffic Mining
 
The Case for a Signal Oriented Data Stream Management System
The Case for a Signal Oriented Data Stream Management SystemThe Case for a Signal Oriented Data Stream Management System
The Case for a Signal Oriented Data Stream Management System
 

S1170136 week8

  • 1. Speaker verification using Oguma histogram S117036 Ami Inoamta Supervisor:M.Sugiyama
  • 2. Outline ● Background ● Oguma histogram ● Speaker verification algorithm ● Speech analysis condition ● Learn histogram , Verification histogram ● Result of speaker verification
  • 3. Background ● Diffusion of smartphone. ● Security is more important. →Speaker verification system ● VQ : most popular. But calculation amount is large. ● Oguma histogram : calculation amount is small. →smartphone application. ● First, test this performance in PC terminal.
  • 4. Oguma histogram ● Do not use VQ. ● Directly make histogram from feature vectors. 1. Set out threshold in each dimension of feature vectors. 2. Compare →Space division 3.Set out Region ID .
  • 6. Speech analysis condition Database TIMIT Dialect region New England Head count 10 person Learning , verification 5 sentence , 5 sentence Recording format wav Sampling rate 16 kHz Dimension number of MFCC 16 Filter bank channel 24 Window size 16 ms Frame shift 8 ms, 16 ms Dimension number of 16, 32, 64, 128, 256 histogram
  • 8. Result of speaker verification Female: Male: Speaker verification result (frame shift 8ms)