14.5.2 MSLS

An execution example is shown in Figure 14.14. After the execution, a file named MFBANK13_0.spec is generated. This file stores little endian 13 dimensional vector sequence expressed in the 32 bit floating-point number format. When separation cannot be performed well, check if the f101b001.wav files are in the data directory.

> ./demo.sh 1
 MSLS 
 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 Figure 14.15 and Figure 14.16. 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 . MSLSExtraction reserves a storing region for the $\delta $ MSLS coefficient other than the MSLS coefficient and outputs vectors that are double of the values specified in the FBANK_COUNT property of MSLSExtraction as a feature (zero is in the storing region for the$\delta $ MSLS coefficient). Therefore, it is necessary to delete the $\delta $ MSLS coefficient domain, which is unnecessary here. Use FeatureRemover to delete it. SaveFeatures saves the input FEATURE. The localization result from the front generated by ConstantLocalization is gave to SOURCES.

Figure 14.15: MAIN (subnet)

Figure 14.16: MAIN_LOOP (iterator)

Table 14.13 summarizes the main modules. The most important module is MSLSExtraction .