14.5.4 MSLS+Power

An execution example is shown in Figure 14.5.4. After the execution, a file named MFBANK14_0.spec is generated. This file stores little endian 14 dimensional vector sequence expressed in the 32 bit floating-point number format. When separation cannot be performed well, check the following items, check if the f101b001.wav is in the ../data directory.

> ./demo.sh 3
 UINodeRepository::Scan()
 Scanning def /usr/lib/flowdesigner/toolbox
 done loading def files
 loading XML document from memory
 done!
 Building network : MAIN

Twelve modules are included in this sample. There are three modules in MAIN_LOOP (iterator) and nine modules in MAIN (subnet). MAIN (subnet) and MAIN_LOOP (iterator) are shown in 14.22 and 14.23 As an outline of the processing, it is simple network configuration in which acoustic features are calculated in MSLSExtraction with the audio waveforms collected in the AudioStreamFromWave module and are written in SaveFeatures . Since MSLSExtraction requires the outputs of the mel-scale filter bank and power spectra for calculation of MSLS, the collected audio waveforms are analyzed by MultiFFT and their data type are converted by MatrixToMap and PowerCalcForMap , and then processing to obtain outputs of the mel-scale filter bank is performed by MelFilterBank . Here, the USE_POWER property of MSLSExtraction is set to trueand to output the power term at the same time. MSLSExtraction reserves a storing region for the $\delta $ MSLS coefficient other than the MSLS coefficient and outputs vectors as a feature (zero is in the storing region for the$\delta $ MSLS coefficient). Since the USE_POWER property is set to true, a storing region of $\delta $ MSLS and the delta power term is secured for the $\delta $ coefficient. Therefore, vectors that are double of the values specified in the FBANK_COUNT property of MSLSExtraction +1 are output as a feature. Outputs other than the necessary MSLS coefficient and item power term are deleted in FeatureRemover . SaveFeatures saves the input FEATURE. The localization result from the front generated by ConstantLocalization is gave to SOURCES.

Figure 14.22: MAIN (subnet)

Figure 14.23: MAIN_LOOP (iterator)

Table 14.16 summarizes the main parameters.