ps_seg_t Struct Reference

Segmentation iterator object. More...

#include <pocketsphinx.h>

Public Member Functions
POCKETSPHINX_EXPORT ps_seg_t *	ps_seg_next (ps_seg_t *seg)
POCKETSPHINX_EXPORT const char *	ps_seg_word (ps_seg_t *seg)
POCKETSPHINX_EXPORT void	ps_seg_frames (ps_seg_t *seg, int *out_sf, int *out_ef)
POCKETSPHINX_EXPORT int32	ps_seg_prob (ps_seg_t *seg, int32 *out_ascr, int32 *out_lscr, int32 *out_lback)
POCKETSPHINX_EXPORT void	ps_seg_free (ps_seg_t *seg)

Detailed Description

Segmentation iterator object.

Member Function Documentation

ps_seg_next()

POCKETSPHINX_EXPORT ps_seg_t * ps_seg_next

(

ps_seg_t *

seg

)

Get the next segment in a word segmentation.

Parameters

seg	Segment iterator.

Returns

Updated iterator with the next segment. NULL at end of utterance (the iterator will be freed in this case).

ps_seg_word()

POCKETSPHINX_EXPORT const char * ps_seg_word

(

ps_seg_t *

seg

)

Get word string from a segmentation iterator.

Parameters

seg	Segment iterator.

Returns

Read-only string giving string name of this segment. This is only valid until the next call to ps_seg_next().

ps_seg_frames()

POCKETSPHINX_EXPORT void ps_seg_frames	(	ps_seg_t *	seg,
		int *	out_sf,
		int *	out_ef
	)

Get inclusive start and end frames from a segmentation iterator.

Note

These frame numbers are inclusive, i.e. the end frame refers to the last frame in which the given word or other segment was active. Therefore, the actual duration is *out_ef - *out_sf + 1.

Parameters

seg	Segment iterator.
out_sf	Output: First frame index in segment.
out_ef	Output: Last frame index in segment.

ps_seg_prob()

POCKETSPHINX_EXPORT int32 ps_seg_prob	(	ps_seg_t *	seg,
		int32 *	out_ascr,
		int32 *	out_lscr,
		int32 *	out_lback
	)

Get language, acoustic, and posterior probabilities from a segmentation iterator.

Note

Unless the -bestpath option is enabled, this function will always return zero (corresponding to a posterior probability of 1.0). Even if -bestpath is enabled, it will also return zero when called on a partial result. Ongoing research into effective confidence annotation for partial hypotheses may result in these restrictions being lifted in future versions.

Parameters

out_ascr	Output: acoustic model score for this segment.
out_lscr	Output: language model score for this segment.
out_lback	Output: language model backoff mode for this segment (i.e. the number of words used in calculating lscr). This field is, of course, only meaningful for N-Gram models.

Returns

Log posterior probability of current segment. Log is expressed in the log-base used in the decoder. To convert to linear floating-point, use logmath_exp(ps_get_logmath(), pprob).

ps_seg_free()

POCKETSPHINX_EXPORT void ps_seg_free

(

ps_seg_t *

seg

)

Finish iterating over a word segmentation early, freeing resources.

---

The documentation for this struct was generated from the following file:

• pocketsphinx.h