Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Speaker Localization, tracking and remote speech pickup in a conference room.
Blekinge Institute of Technology, School of Engineering.
2009 (English)Independent thesis Advanced level (degree of Master (Two Years))Student thesisAlternative title
Speaker Lokalisering, spårning och avlägsna tal pickup i ett konferensrum (Swedish)
Abstract [en]

Effective speech communication using microphone Array is getting significant research in speech acquisition methods such as speaker localization and tracking. Localization techniques play an important role for automatic camera in videoconferencing system and for other human machine interfaces. To locate the accurate Direction Of Arrival (DOA) from the source, it is necessary to design a suitable microphone array system with minimum internal hardware noise and more efficient localization algorithm. There are many algorithms developed for estimating the number of sources and locating the DOA, such as Bayesian algorithm, kalman filtering, Generalized Cross Correlation (GCC) and Steered Response Power (SRP) algorithm. But SRP algorithm with its steered beam forming technique for speaker localization is more robust using microphone array. The Phase Alignment Transform (PHAT) has gained a lot of attention in the recent research for its quite robust response in low noise, but reverberant environment. So combining SRP-PHAT will become the robust localizer in reverberant environment. This project aims at designing and installing a remote speech pickup system functioning as a frontend to a VoIP system in the biometric lab. A large microphone array is designed and installed on the ceiling of the biometric lab and integrated it with a signal processing software suit for speaker localization and tracking, SRP-PHAT algorithm is used as a localizer. Experiments were done on real time recorded data of human talkers. The algorithm gives accurate DOA from the dominant speaker and is suitable for real time processing.

Abstract [sv]

Effektiv talkommunikation med mikrofoner blir betydande forskning inom metoder tal förvärv som talare lokalisering och spårning. Localization tekniker spelar en viktig roll för automatisk kamera i videokonferenssystem och för andra människors maskin gränssnitt. För att hitta exakt Direction of Arrival (DOA) från källan, är det nödvändigt att utforma ett lämpligt system mikrofoner med minsta inre hårdvara buller och effektivare lokalisering algoritm. Det finns många algoritmer utvecklats för att uppskatta antalet källor och placera DOA, såsom Bayesian algoritm, Kalman filtrering, Generalized Cross Correlation (GCC) och styrde Response Power (SRP) algoritm. Men SRP algoritm med de styrda strålar teknik för högtalare lokalisering är mer robust med mikrofoner. Fas Justering Transform (PHAT) har fått stor uppmärksamhet i den senaste forskningen för dess ganska robust svar i lågt brus, men efterklangsfält miljö. Så kombinera SRP-PHAT kommer att bli den robusta localizer i efterklangsfält miljö. Detta projekt syftar till att utforma och installera ett fjärrsystem tal pickup fungerar som ett gränssnitt till ett VoIP-system i biometriska labbet. En stor mikrofoner är konstruerad och installerad på taket av biometriska labbet och integrerat den med en signal programvara passar för högtalare lokalisering och spårning, SRP-PHAT algoritm används som localizer. Experiment gjordes på realtid registrerade uppgifter mänskliga talare. Algoritmen ger exakta DOA från den dominerande högtalare och är lämplig för realtidsbearbetning.

Place, publisher, year, edition, pages
2009. , 47 p.
Keyword [en]
Speaker Localization, tracking, SRP-PHAT.
National Category
Signal Processing
Identifiers
URN: urn:nbn:se:bth-4324Local ID: oai:bth.se:arkivexF9BBBE89AF99CF55C12576620040B35FOAI: oai:DiVA.org:bth-4324DiVA: diva2:831657
Uppsok
Technology
Supervisors
Note
Cell number: 0046-700183434Available from: 2015-04-22 Created: 2009-11-02 Last updated: 2015-06-30Bibliographically approved

Open Access in DiVA

fulltext(692 kB)203 downloads
File information
File name FULLTEXT01.pdfFile size 692 kBChecksum SHA-512
27849411460d64c21a2da285bf235d0c9d85c2711a73f2efd6b4e012eaa87496abc33e5da800eebda380b817fc9065c95d9be7a8df5e0eaf8078d94159737c46
Type fulltextMimetype application/pdf

By organisation
School of Engineering
Signal Processing

Search outside of DiVA

GoogleGoogle Scholar
Total: 203 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 55 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf