Displaying 11 results from an estimated 11 matches for "speech_prob_continue".
2007 Nov 05
2
[patch] speex_preprocess_ctl
...ixes a valid issue, but I'm not an expert.
> Anyways, I didn't see and follow-up or reply...
>
> Cheers,
> Mihai
>
> On Oct 29, 2007, at 7:14 PM, Mikael Magnusson wrote:
>
> > There is a problem in speex_preprocess_ctl. Both speech_prob_start
> > and speech_prob_continue are set to 327.67 for all input values
> > except 0 which results in 0. This is in floating point mode.
> >
> > I think the included patch fixes the problem.
> >
> > Mikael
> > Index: libspeex/preprocess.c
> > =============================================...
2007 Oct 29
1
[patch] speex_preprocess_ctl
There is a problem in speex_preprocess_ctl. Both speech_prob_start and
speech_prob_continue are set to 327.67 for all input values except 0
which results in 0. This is in floating point mode.
I think the included patch fixes the problem.
Mikael
-------------- next part --------------
Index: libspeex/preprocess.c
===================================================================
--- li...
2004 Aug 06
2
Memory leak in denoiser + a few questions
On Mar 28, 2004, at 8:23 PM, Jean-Marc Valin wrote:
>> The st->zeta pointer isn't freed in the
>> speex_preprocess_state_destroy()
>> function of the preprocess.c file (alloced in line 167). It's in
>> Speex 1.1.4
>> by the way.
>
> Oops... Thanks for letting me know. I'll change that for the next
> release (in the mean time, the fix is
2004 Aug 06
4
Memory leak in denoiser + a few questions
...ss.c,v
retrieving revision 1.2
retrieving revision 1.3
diff -u -w -r1.2 -r1.3
--- preprocess.c 2003/11/07 23:40:23 1.2
+++ preprocess.c 2004/02/06 17:10:24 1.3
@@ -145,6 +145,9 @@
st->agc_level = 8000;
st->vad_enabled = 0;
+ st->speech_prob_start = SPEEX_PROB_START ;
+ st->speech_prob_continue = SPEEX_PROB_CONTINUE ;
+
st->frame = (float*)speex_alloc(2*N*sizeof(float));
st->ps = (float*)speex_alloc(N*sizeof(float));
st->gain2 = (float*)speex_alloc(N*sizeof(float));
@@ -435,12 +438,19 @@
st->speech_prob = p0/(1e-25+p1+p0);
/*fprintf (stderr, "...
2007 Nov 05
0
[patch] speex_preprocess_ctl
...#39;m not an expert.
>> Anyways, I didn't see and follow-up or reply...
>>
>> Cheers,
>> Mihai
>>
>> On Oct 29, 2007, at 7:14 PM, Mikael Magnusson wrote:
>>
>>> There is a problem in speex_preprocess_ctl. Both speech_prob_start
>>> and speech_prob_continue are set to 327.67 for all input values
>>> except 0 which results in 0. This is in floating point mode.
>>>
>>> I think the included patch fixes the problem.
>>>
>>> Mikael
>>> Index: libspeex/preprocess.c
>>> ==========================...
2008 Feb 12
0
Second part of data export patch
...s_size) */
@@ -994,9 +996,10 @@
st->outbuf[i] = st->frame[st->frame_size+i];
/* FIXME: This VAD is a kludge */
+ st->speech_prob = Pframe;
if (st->vad_enabled)
{
- if (Pframe > st->speech_prob_start || (st->was_speech && Pframe > st->speech_prob_continue))
+ if (st->speech_prob > st->speech_prob_start || (st->was_speech && st->speech_prob > st->speech_prob_continue))
{
st->was_speech=1;
return 1;
@@ -1191,6 +1194,9 @@
for(i=0;i<st->ps_size;i++)
((spx_int32_t *)ptr)...
2011 Aug 29
3
Speex VAD always returning 1
From 1.2rc1 source code:
preprocess.c:
/* FIXME: This VAD is a kludge */
st->speech_prob = Pframe;
if (st->vad_enabled)
{
if (st->speech_prob > st->speech_prob_start || (st->was_speech &&
st->speech_prob > st->speech_prob_continue))
{
st->was_speech=1;
return 1;
} else
{
st->was_speech=0;
return 0;
}
} else {
return 1;
}
AND
case SPEEX_PREPROCESS_SET_VAD:
speex_warning("The VAD has been replaced by a hack pending a complete
rewrite");
st->vad_enabled = (*(spx_int32_t*)ptr);
break;
As you can see, it i...
2010 Jun 07
0
No subject
preprocess.c:
/* FIXME: This VAD is a kludge */
st->speech_prob =3D Pframe;
if (st->vad_enabled)
{
if (st->speech_prob > st->speech_prob_start || (st->was_speech && st->speec=
h_prob > st->speech_prob_continue))
{
st->was_speech=3D1;
return 1;
} else
{
st->was_speech=3D0;
return 0;
}
} else {
return 1;
}
AND
case SPEEX_PREPROCESS_SET_VAD:
speex_warning("The VAD has been replaced by a hack pending a complete rewri=
te");
st->vad_enabled =3D (*(spx_int32_t*)ptr);
break;
As you can se...
2010 Jun 07
0
No subject
preprocess.c:
/* FIXME: This VAD is a kludge */
st->speech_prob =3D Pframe;
if (st->vad_enabled)
{
if (st->speech_prob > st->speech_prob_start || (st->was_speech && st->speec=
h_prob > st->speech_prob_continue))
{
st->was_speech=3D1;
return 1;
} else
{
st->was_speech=3D0;
return 0;
}
} else {
return 1;
}
AND
case SPEEX_PREPROCESS_SET_VAD:
speex_warning("The VAD has been replaced by a hack pending a complete rewri=
te");
st->vad_enabled =3D (*(spx_int32_t*)ptr);
break;
As you can se...
2011 Aug 29
0
Speex VAD always returning 1
...e:
> From 1.2rc1 source code:
>
> preprocess.c:
>
> /* FIXME: This VAD is a kludge */
> st->speech_prob = Pframe;
> if (st->vad_enabled)
> {
> if (st->speech_prob > st->speech_prob_start || (st->was_speech &&
> st->speech_prob > st->speech_prob_continue))
> {
> st->was_speech=1;
> return 1;
> } else
> {
> st->was_speech=0;
> return 0;
> }
> } else {
> return 1;
> }
>
> AND
>
> case SPEEX_PREPROCESS_SET_VAD:
> speex_warning("The VAD has been replaced by a hack pending a complete
> rewrit...
2011 Aug 29
2
Speex VAD always returning 1
I have been trying to understand how to get the VAD algorithm working. I sent an input stream of all zeros into the preprocessor but still got a return value of 1 indicating that speech was detected. Is this feature not available with the latest release? I thought at the very least it would detect this as silence and return 0 but that does not seem to be the case.
Does anyone have any