sspmod_spch_det.c File Reference

Speech Detection. More...

Data Structures
struct	SprSDFX
struct	SprSDKD

Functions
void	spr_sd_free (SprSspInfo *Info)
int	spr_sd_setup (SprSspInfo *Info, const char **descript, void *aux_info)
int	spr_SD_KD_process (SprSDKD *sd, float x)
void	spr_SD_KD_reset (SprSDKD *sd)
int	spr_sd_process (SprSspInfo *Info, const void *frame_in, void *frame_out)
void	spr_sd_reset (SprSspInfo *Info, SprSspStatus *action)

Detailed Description

Speech Detection.

Speech detection based on energy. All parameters are set for detection on power values, so energy should not be in dB!

---

[speech_detect]
method <FX/KD>(FX)
Speech detection algorithm to be used.
db2pow
Input is in Db, convert first to power levels as required by the speech detectors.
reset <yes/no>(yes)
Reset the speech detectors at the beginning of each new file.
multi_spkr <N> <copy/move> <buf_name>
Setup the sil/spch detector to work in a multi-speaker environment, i.e. noise/speech statisctics for the N last (leat recent used) speaker id's are calculated. The speaker id's are input from a named buffer.
sil_range <min_range>(0.0) <max_range>(0.0)
KD: The <min_range> parameter is needed for signals that are almost noise free, and gives a lower bound on the amplitude of the noise. The <max_range> gives an upper bound on the amplitude of the noise, and gives more robustness if the speech detector is started in a speech segment.
spch_raise <raise>(0.25)
KD: minimum raise in the speech level (averaged over 4 consecutive frames) needed to detect the very first word.
spch_range <range>(20.0)
KD: signals (amplitude) below the average speech level divided by <range> are also treated as noise.

---

See Also

ssp_master.c

Author

Fei Xie (algorithm)

Tom Claes (implementation of functions)

Kris Demuynck (second method)

Date

16 Aug 1995

Revision History:

Sep 1998 - KD

added a second method

Feb 2004 - KD

modified to cope with multiple conditions