In this paper, a new method for making v/uv decision is developed which uses a multi-feature v/uv classification algorithm based on the analysis of cepstral peak, zero crossing rate, and autocorrelation function (ACF)...In this paper, a new method for making v/uv decision is developed which uses a multi-feature v/uv classification algorithm based on the analysis of cepstral peak, zero crossing rate, and autocorrelation function (ACF) peak of short-time segments of the speech signal by using some clustering methods. This v/uv classifier achieved excellent results for identification of voiced and unvoiced segments of speech.展开更多
Unvoiced/voiced classification of speech is a challenging problem especially under conditions of low signal-to-noise ratio or the non-white-stationary noise environment. To solve this problem, an algorithm for speech ...Unvoiced/voiced classification of speech is a challenging problem especially under conditions of low signal-to-noise ratio or the non-white-stationary noise environment. To solve this problem, an algorithm for speech classification, and a technique for the estimation of palrwise magnitude frequency in voiced speech am proposed. By using third order spectrum of speech signal to remove noise, in this algorithm the least spectrum difference to get refined pitch and the max harmonic number is given. And this algorithm utilizes spectral envelope to estimate signal-to-noise ratio of speech harmonics. Speech classification, voicing probability, and harmonic parameters of the voiced frame can be obtained. Simulation results indicate that the proposed algorithm, under complicated background noise, especially Gaussian noise, can effectively classify speech in high accuracy for voicing probability and the voiced parameters.展开更多
文摘In this paper, a new method for making v/uv decision is developed which uses a multi-feature v/uv classification algorithm based on the analysis of cepstral peak, zero crossing rate, and autocorrelation function (ACF) peak of short-time segments of the speech signal by using some clustering methods. This v/uv classifier achieved excellent results for identification of voiced and unvoiced segments of speech.
文摘Unvoiced/voiced classification of speech is a challenging problem especially under conditions of low signal-to-noise ratio or the non-white-stationary noise environment. To solve this problem, an algorithm for speech classification, and a technique for the estimation of palrwise magnitude frequency in voiced speech am proposed. By using third order spectrum of speech signal to remove noise, in this algorithm the least spectrum difference to get refined pitch and the max harmonic number is given. And this algorithm utilizes spectral envelope to estimate signal-to-noise ratio of speech harmonics. Speech classification, voicing probability, and harmonic parameters of the voiced frame can be obtained. Simulation results indicate that the proposed algorithm, under complicated background noise, especially Gaussian noise, can effectively classify speech in high accuracy for voicing probability and the voiced parameters.
