Low Complexity Speaker Identification in AAC Domain

• AI Haojun

  National Engineering Research Center for Multimedia Software, Wuhan University:Graduate School of Information Science and Technology, Hokkaido University

• HASEYAMA Miki

  Graduate School of Information Science and Technology, Hokkaido University

抄録

This paper presents an implementation of a low-complexity speaker identification algorithm working in the compressed audio domain. The goal is to perform speaker modeling and identification without decoding the AAC bitstream to extract speaker dependent features, thus saving important system resource. The silence detection and MFCC parameters are calculated from MDCT coefficient other than from the FFT spectrum. Each speaker is modeled by a GMM, which is trained using the EM algorithm to refine the weight and the parameters of each component. The recognition accuracies of our algorithm reach 97% for ARCTIC database with 16% CPU overload comparing to the algorithms based on the analysis of the decoded PCM signals.

収録刊行物

• 映像情報メディア学会技術報告

  映像情報メディア学会技術報告 32.46 (0), 31-34, 2008

  一般社団法人 映像情報メディア学会

キーワード

• Speaker Recognition
• Discrete Cosine Transforms
• Audio coding

詳細情報

• CRID: 1390001204525609344
• NII論文ID: 110007385516
• NII書誌ID: AN1059086X
• DOI: 10.11485/itetr.32.46.0_31
• ISSN: 24241970
• ISSN: 13426893
• NDL書誌ID: 9709697
• Web Site: http://id.ndl.go.jp/bib/9709697
• Web Site: https://ndlsearch.ndl.go.jp/books/R000000004-I9709697
• 本文言語コード: en
• データソース種別:
  • JaLC
  • NDL
  • CiNii Articles
• 抄録ライセンスフラグ: 使用不可