"Detektor \u0159e\u010Dov\u00E9 aktivity zalo\u017Een\u00FD na statistick\u00FDch metod\u00E1ch"@cs . "549680" . "P(1ET301710509), P(GA102/04/1097), Z(MSM0021630513)" . "This paper deals with the method of voice activity detection. Rising requirements to applications with variable-rate speech coding also increases the role of voice activity detectors which become crucial for the efficient bandwidth reduction. The paper aims especially to two detector types; these are the detector based on short-time signal energy and statistical model-based voice activity detector. Decision-making rules of the statistical model-based detector are derived from the LRT (Likelihood Ratio TTest) by estimating unknown parameters using the ML (Maximum Likelihood) criterion. In addition there is an effective hang-over scheme based on HMM (Hidden Markov Model) principles in the detector. There were models for these detectors created in Matlab simulation environment. Models were tested on voice signals with the white noise as well as real noises. The results were evaluated and compared for various types of noises and SNR (Signal to Noise Ratios) values."@en . "RIV/00216305:26220/05:PU51360!RIV06-GA0-26220___" . . "175-180" . "1"^^ . "RIV/00216305:26220/05:PU51360" . "Sysel, Petr" . . . . "P\u0159\u00EDsp\u011Bvek se v\u011Bnuje metod\u00E1m detekce \u0159e\u010Dov\u00E9ho sign\u00E1lu. Se vzr\u016Fstaj\u00EDc\u00EDm po\u010Dtem aplikac\u00ED \u0161irokop\u00E1smov\u00E9ho k\u00F3dov\u00E1n\u00ED \u0159e\u010Di se zvy\u0161uje \u00FAloha detektor\u016F \u0159e\u010Dov\u00E9 aktivity s ohledem na dosa\u017Een\u00ED co neju\u017E\u0161\u00EDho p\u00E1sma. P\u0159\u00EDsp\u011Bvek se zam\u011B\u0159uje na dva typy detektor\u016F; je to detektor zalo\u017Een\u00FD na sledov\u00E1n\u00ED kr\u00E1tkodob\u00E9 energie sign\u00E1lu a detektor zalo\u017Een\u00FD na statistick\u00FDch metod\u00E1ch. Rozhodovac\u00ED pravidlo statistick\u00E9ho detektoru je odvozeno od testu maxim\u00E1ln\u00ED podobnosti LRT (Likelihood Ratio Test), kdy nezn\u00E1m\u00E9 parametry jsou odhadnutty metodou maxim\u00E1ln\u00ED podobnosti ML (Maximum Likelihood). Nav\u00EDc je dopln\u011Bn efektivn\u00EDm modelem p\u0159echodu mezi \u0159e\u010Dov\u00FDmi a \u0161umov\u00FDmi segmenty zalo\u017Een\u00FDm na skryt\u00FDch Markovov\u00FDch \u0159et\u011Bzc\u00EDch. Oba detektory byly simulov\u00E1ny v prost\u0159ed\u00ED Matlab a byly testov\u00E1ny na r\u016Fzn\u00FDch nahr\u00E1vk\u00E1ch obsahuj\u00EDc\u00EDch um\u011Bl\u00E9 i re\u00E1ln\u00E9 hluky pro r\u016Fzn\u00E9 pom\u011Bry sign\u00E1lu od \u0161umu."@cs . "1"^^ . "voice activity detector statistical model"@en . "This paper deals with the method of voice activity detection. Rising requirements to applications with variable-rate speech coding also increases the role of voice activity detectors which become crucial for the efficient bandwidth reduction. The paper aims especially to two detector types; these are the detector based on short-time signal energy and statistical model-based voice activity detector. Decision-making rules of the statistical model-based detector are derived from the LRT (Likelihood Ratio TTest) by estimating unknown parameters using the ML (Maximum Likelihood) criterion. In addition there is an effective hang-over scheme based on HMM (Hidden Markov Model) principles in the detector. There were models for these detectors created in Matlab simulation environment. Models were tested on voice signals with the white noise as well as real noises. The results were evaluated and compared for various types of noises and SNR (Signal to Noise Ratios) values." . . "2005-09-26+02:00"^^ . . . . . "Voice Activity Detection based-on Statistic Models" . . "Proceedings of the 16th Conference Electronic Speech Signal Processing" . . "6"^^ . . . "Prague, Czech Republic" . . . "Detektor \u0159e\u010Dov\u00E9 aktivity zalo\u017Een\u00FD na statistick\u00FDch metod\u00E1ch"@cs . "\u00DAstav radiotechniky a elektroniky AV \u010CR" . . "Voice Activity Detection based-on Statistic Models" . "Prague, Lichenstein Palace" . . "[D502D18135FD]" . "26220" . "Voice Activity Detection based-on Statistic Models"@en . "3-938863-17-X" . "Voice Activity Detection based-on Statistic Models"@en .