Real-Time, Non-intrusive Speech Quality Estimation: A Signal-Based Model

Created by W.Langdon from gp-bibliography.bib Revision:1.4496

  title =        "Real-Time, Non-intrusive Speech Quality Estimation:
                 {A} Signal-Based Model",
  author =       "Adil Raja and Colin Flanagan",
  bibdate =      "2008-04-15",
  bibsource =    "DBLP,
  booktitle =    "Proceedings of the 11th European Conference on Genetic
                 Programming, EuroGP 2008",
  address =      "Naples",
  month =        "26-28 " # mar,
  publisher =    "Springer",
  year =         "2008",
  volume =       "4971",
  editor =       "Michael O'Neill and Leonardo Vanneschi and 
                 Steven Gustafson and Anna Isabel {Esparcia Alcazar} and 
                 Ivanoe {De Falco} and Antonio {Della Cioppa} and 
                 Ernesto Tarantino",
  isbn13 =       "978-3-540-78670-2",
  pages =        "37--48",
  series =       "Lecture Notes in Computer Science",
  DOI =          "doi:10.1007/978-3-540-78671-9_4",
  abstract =     "Speech quality estimation, as perceived by humans, is
                 of vital importance to proper functioning of
                 telecommunications networks. Speech quality can be
                 degraded due to various network related problems. In
                 this paper we present a model for speech quality
                 estimation that is a function of various time and
                 frequency domain features of human speech. We have
                 employed a hybrid optimisation approach, by using
                 Genetic Programming (GP) to find a suitable structure
                 for the desired model. In order to optimize the
                 coefficients of the model we have employed a
                 traditional GA and a numerical method known as linear
                 scaling. The proposed model outperforms the ITU-T
                 Recommendation P.563 in terms of prediction accuracy,
                 which is the current non-intrusive speech quality
                 estimation model. The proposed model also has a
                 significantly reduced dimensionality. This may reduce
                 the computational requirements of the model.",
  keywords =     "genetic algorithms, genetic programming,
                 Non-Intrusive, Signal-based, GP, MOS",
  notes =        "Part of \cite{conf/eurogp/2008} EuroGP'2008 held in
                 conjunction with EvoCOP2008, EvoBIO2008 and

Genetic Programming entries for Adil Raja Colin Flanagan