"RIV/00216305:26220/06:PU64281!RIV07-GA0-26220___" . "[0A74D77577E2]" . . . "Noise cancellation algorithms for speech signal distorted in telecommunication networks." . "This paper aims to provide an evaluation of the effectiveness of three different speech noise power spectrum estimation algorithms The evaluation of their efficiency was based on the hit rate recognition obtained at the output of an HMM phoneme based speech recognizer. Noisy speech consisted of 100 speech sentences randomly extracted from the NTIMIT database. The best speech noise power spectrum estimator proved to be a procedure based on the arithmetic average of the power spectrums obtained from signal frames where no speech activity was detected. The noise spectrum estimate provide by either a four layer MLP neural network, or an Adaptive Neural Fuzzy Inference System (ANFIS) proved to give lower performance than the average noise spectrum estimator, even though both of them are able to detect some of the noise features and the ANFIS performance are better than those obtained from the MLP neural network."@en . "7"^^ . . . "Tento \u010Dl\u00E1nek ukazuje mo\u017Enost vyu\u017Eit\u00ED syst\u00E9m\u016F um\u011Bl\u00E9 inteligence v algoritmech pro zv\u00FDrazn\u011Bn\u00ED \u0159e\u010Di v hlu\u010Dn\u00E9m pozad\u00ED. \u010Cl\u00E1nek porovn\u00E1v\u00E1 efektivitu t\u0159\u00ED odli\u0161n\u00FDch syst\u00E9m\u016F pro potla\u010Den\u00ED \u0161umu zalo\u017Een\u00FDch na metod\u011B spektr\u00E1ln\u00ED subtrakce. Prvn\u00ED syst\u00E9m odhaduje spektrum \u0161umu na z\u00E1klad\u011B jeho statistick\u00FDch vlastnost\u00ED. Dal\u0161\u00ED dva syst\u00E9my odhaduj\u00ED spektrum \u0161umu pomoc\u00ED neline\u00E1rn\u00EDch adaptivn\u00EDch model\u016F. Efektivita popsan\u00FDch algoritm\u016F je vyhodnocena na z\u00E1klad\u011B \u00FAsp\u011B\u0161nosti rozpozn\u00E1n\u00ED zpracovan\u00FDch \u0159e\u010Dov\u00FDch nahr\u00E1vek po\u010D\u00EDta\u010Dov\u00FDm rozpozn\u00E1va\u010Dem \u0159e\u010Di zalo\u017Een\u00FDm na skryt\u00FDch Markovov\u00FDch modelech. Algoritmy jsou testov\u00E1ny na datab\u00E1zi NTIMIT obsahuj\u00EDc\u00ED kr\u00E1tk\u00E9 nahr\u00E1vky \u0159e\u010Dov\u00FDch promluv p\u0159enesen\u00E9 skute\u010Dnou telekomunika\u010Dn\u00ED s\u00EDt\u00ED americk\u00E9 firmy NYTEX."@cs . "Noise cancellation algorithms for speech signal distorted in telecommunication networks." . "Praha" . "Noise cancellation algorithms for speech signal distorted in telecommunication networks."@en . "16th Czech-German Workshop on speech processing" . "Algoritmy pro odstra\u0148ov\u00E1n\u00ED \u0161umu v \u0159e\u010Di zkreslen\u00E9 telekomunika\u010Dn\u00ED s\u00EDt\u00ED"@cs . "488756" . "spectral subtraction, thresholdig, neural network, ANFIS, speech recognizer"@en . "1"^^ . "1-7" . . . . "\u010Desk\u00E1 republika, Praha" . "1"^^ . "80-86269-15-9" . . . "P(GA102/06/1233), Z(MSM0021630513)" . . . "RIV/00216305:26220/06:PU64281" . . . . . "\u00DAstav radiotechniky a elektroniky AV \u010CR" . . "Algoritmy pro odstra\u0148ov\u00E1n\u00ED \u0161umu v \u0159e\u010Di zkreslen\u00E9 telekomunika\u010Dn\u00ED s\u00EDt\u00ED"@cs . . "Noise cancellation algorithms for speech signal distorted in telecommunication networks."@en . "Koula, Ivan" . "26220" . "This paper aims to provide an evaluation of the effectiveness of three different speech noise power spectrum estimation algorithms The evaluation of their efficiency was based on the hit rate recognition obtained at the output of an HMM phoneme based speech recognizer. Noisy speech consisted of 100 speech sentences randomly extracted from the NTIMIT database. The best speech noise power spectrum estimator proved to be a procedure based on the arithmetic average of the power spectrums obtained from signal frames where no speech activity was detected. The noise spectrum estimate provide by either a four layer MLP neural network, or an Adaptive Neural Fuzzy Inference System (ANFIS) proved to give lower performance than the average noise spectrum estimator, even though both of them are able to detect some of the noise features and the ANFIS performance are better than those obtained from the MLP neural network." . "2006-09-27+02:00"^^ . . . .