论文部分内容阅读
An auxiliary vector particle filter was proposed to present the vocal tract resonances (VTRs) tracking.It uses particle filter based on a version of state-space model that describes the characteristics of speech signal.The speech model consists of a target-guided dynamic function and a non-linear prediction mapping from resonance frequencies and bandwidths to LPC cepstra(LPCC).There are two characteristics in the proposed method.First,particle filtering technique is put forth to solve the non-linear problem of speech model.Second,an auxiliary vector,embedded in the state function of speech model,is applied to incorporate the most current observations and to generate the proposal distribution of particle filter.The experimental results show that this method is able to track the VTRs of continuous speech utterance efficiently with a small number of particles and able to solve the problem of spurious peaks and merging peaks.
An auxiliary vector particle filter was proposed to present the vocal tract resonances (VTRs) tracking. It uses particle filter based on a version of state-space model that describes the characteristics of speech signal. The speech model consists of a target-guided dynamic function and a non-linear prediction mapping from resonance frequencies and bandwidths to LPC cepstra (LPCC). There are two characteristics in the proposed method. First, particle filtering technique is put forth to solve the non-linear problem of speech model. Second, an auxiliary vector, embedded in the state function of speech model, is applied to incorporate the most current observations and to generate the proposal distribution of particle filter. The experimental results show that this method is able to track the VTRs of continuous speech utterance efficiently with a small number of particles and able to solve the problem of spurious peaks and merging peaks.