SPro For Linux

SPro is a free speech signal processing toolkit which provides runtime commands implementing standard feature extraction algorithms for speech related applications and a C library to implement new algorithms and to use SPro files within your own programs.

SPro was originally designed for variable resolution spectral analysis but also provides for feature extraction techniques classically used in speech applications.

� waveform signal input � low-level signal processing (FFT, LPC analysis, etc.) � low-level feature processing (lifter, CMS, variance normalization, deltas, etc.) � feature I/O

The library does not provide for high-level feature extraction functions which directly converts a waveform into features, mainly because such functions would require a tremendous number of arguments in order to be versatile. However, it is rather trivial to write such a function for your particular needs using the SPro library.

What's New in This Release:

� SPro 4.0 is not compatible with previous releases and exhibits major changes in its structure. The main difference is the introduction of feature streams (much alike the signal streams used for input). This new feature I/O mechanisms enables the processing of continuous (or very large) audio streams. � As introducing feature streams required a *major* redesign of the source code, all the library files have been profondly modified and, to avoid confusions, old spro_*.c names have been changed. Aslo, the SPRO FEATURE FILE FORMAT HAS CHANGED to accomodate for streams (e.g. number of frames unknown)... � feature I/O via feature streams � redefined SPro feature file format which now includes an optional variable length ASCII header. � added LSF computation in slpc � added normalization qualifier (R) � delta, delta-delta, CMS can be computed directly in the main tools