


NPOINT(UCL1)      MISC. REFERENCE MANUAL PAGES       NPOINT(UCL1)



NAME
     npoint - endpoint N utterances in a single speech waveform

SYNOPSIS
     npoint (-i item) (-n numutter)  (-r  mark_space_ratio%)  (-b
     backofftime) (-w windowtime) file

DESCRIPTION
     npoint is a program to automatically annotate the  endpoints
     of multiple utterances in a speech waveform.  The input is a
     speech signal containing one or more utterances (the  number
     specified on command line) separated by silence.  The output
     is 2N annotations, marking the beginning  and  end  of  each
     utterance.  The program uses a dynamic programming procedure
     to find exactly N utterances and N+1 silences.

OPTIONS
     -I         Identify program name and version number.

     -iitem     Select input item number.

     -nnumutter Specify number of utterances. Default 1.

     -rmark_space
                Specify the mark-to-space ratio for  speech  sig-
                nals  to silence.  This is expressed as a percen-
                tage in range 0-100.  Thus for  2  second  utter-
                ances   separated   typically  by  5  seconds  of
                silence,  specify  a  mark-space  ratio  of   40.
                Default 50.

     -bbackofftime
                Specify the time in seconds you want the  markers
                'backed-off'  from  the  located  start  and stop
                points.  The start markers are moved  earlier  by
                this  time,  the stop markes are moved later.  No
                check is performed to see if this  causes  starts
                to overlap previous stops.  Default 0.1s.

     -wwindowtime
                Specify the  size  of  each  analysis  window  in
                seconds.  Annotations are positioned to multiples
                of this size.  The maximum size  of  speech  file
                that can be processed is limited by the square of
                the number of analysis windows required to  cover
                the input.  So for an input signal of 30 seconds,
                a window of 0.05 seconds will required 600x600  =
                360kbytes  of memory. To analyse long speech sig-
                nals use a larger analysis window.  Default  0.05
                seconds.





SFS                     Last change: UCL                        1






NPOINT(UCL1)      MISC. REFERENCE MANUAL PAGES       NPOINT(UCL1)



INPUT ITEMS
     SP         Speech pressure waveform.

OUTPUT ITEMS
     AN         Endpoint annotations: {startN,stopN}.

HISTORY
     utterances number of utterances.

     markspace  mark-to-space ratio

     windowtime analysis window size (s).

     backoff    back-off time (s)

     type       set to 'endpoints'.

VERSION/AUTHOR
     1.1        Mark Huckvale

BUGS
SOURCE
     /ptemp/mark/sfs/ucl/npoint.c
































SFS                     Last change: UCL                        2



