次へ: Experiments
上へ: Multipitch Detection Algorithm
戻る: Detection of the number
Detection of s and Spectral Envelopes
In the previous process, the ML procedure allows to aqcuire local
optimal solutions of without distinction of the true s or the multiples of the true s.
Therefore, the true s must somehow be discovered by replacing
each by each to their multiples.
Consider now that a degree of freedom is given to every and consequently
allows to extract the spectral envelope, i.e., the relative amplitudes of
the partials.
If is lower than the true , the model must be
overfit. From this point of
view, the problem of obtaining the true s and the spectral envelope can
also be handled with the information criterion. The process shown below is done with
all remaining tiedGMMs after the previous process.
 Replace the representative means to
where is an integer number whose initial value is 1. The number
of Gaussians limited below the Nyquist logfrequency is denoted as
.
 Estimate the ML model parameters by EM algorithm. Here we only
update and should be updated to



(13) 
 Calculate AIC with equation (9). The number of free parameters here
is . If the AIC increases, the process should be
interrupted and the
is considered as
the detected , and if not, add to and return to step1.
図:
Detected contour of a single speaker
図:
Reference contour corresponding to Figure 3

表 1:
Results for a single speaker

Accuracy(%) 
Speech file 
Cepstrum 
Proposed 
`myisda01' 
88.2 
98.0 
`myisda02' 
88.4 
99.0 
`myisda03' 
84.8 
98.1 
`myisda04' 
85.1 
92.4 
`myisda05' 
76.8 
93.7 
`fymsda01' 
86.3 
98.5 
`fymsda02' 
87.1 
97.5 
`fymsda03' 
83.3 
95.8 
`fymsda04' 
86.7 
96.8 
`fymsda05' 
85.2 
96.0 
次へ: Experiments
上へ: Multipitch Detection Algorithm
戻る: Detection of the number
平成16年3月25日