ref: e62621b8f19ca1a4ae852c6bfd9a54a81e2f124a
parent: 15ba7f5fa46fe8a17d1f56a15598923ca9ea4c1a
author: robs <robs>
date: Thu May 21 11:53:36 EDT 2009
spectrogram -X
--- a/ChangeLog
+++ b/ChangeLog
@@ -85,6 +85,7 @@
o New `biquad' filter effect using external coefficients. (robs)
o New `overdrive' effect. (robs)
o New `pluck' and `tpdf' types for `synth'. (robs)
+ o New `-X duration' option for `spectrogram'. (robs)
o [2778142] just intonation for `synth'. (robs)
o Can now set common parameters for multiple `synth' channels. (robs)
o Richer gain/normalise options. (robs)
--- a/sox.1
+++ b/sox.1
@@ -1798,18 +1798,30 @@
effects.
.TP
\fBdcshift \fIshift\fR [\fIlimitergain\fR]
-DC Shift the audio, with basic linear amplitude formula.
-This is most useful if your audio tends to not be centred around
-a value of 0. Shifting it back will allow you to get the most volume
-adjustments without clipping.
+Apply a DC shift to the audio. This can be useful to remove a DC
+offset (caused perhaps by a hardware problem in the recording chain)
+from the audio. The effect of a DC offset is reduced headroom and
+hence volume.
+The
+.B stat
+or
+.B stats
+effect can be used to determine if a signal has a DC offset.
.SP
-The first option is the \fIdcshift\fR value. It is a floating point number that
-indicates the amount to shift.
+The given \fIdcshift\fR value is a floating point number in the range
+of \(+-2 that indicates the amount to shift the audio (which is in the
+range of \(+-1).
.SP
An optional
.I limitergain
can be specified as well. It should have a value much less than 1
(e.g. 0\*d05 or 0\*d02) and is used only on peaks to prevent clipping.
+.TS
+center;
+c8 c8 c.
+* * *
+.TE
+.DT
.SP
An alternative approach to removing a DC offset (albeit with a short delay)
is to use the
@@ -1820,10 +1832,6 @@
sox -n dc.wav synth 5 sin %0 50
sox dc.wav fixed.wav highpass 10
.EE
-.SP
-See also the
-.B stats
-effect.
.TP
\fBdeemph\fR
Apply ISO 908 de-emphasis (a treble attenuation shelving filter) to
@@ -3109,8 +3117,8 @@
and need not be an integer. SoX
may make a slight adjustment to the given number for processing
quantisation reasons; if so, SoX will report the actual number used
-(viewable when
-.B \-\-verbose
+(viewable when the SoX global option
+.B \-V
is in effect).
.SP
The maximum width of the spectrogram is 999 pixels; if the audio length
@@ -3125,6 +3133,25 @@
sox audio.ogg -n trim 1:00 spectrogram
.EE
starts the spectrogram at 1 minute through the audio.
+.SP
+See also
+.B \-X
+for an alternative way of setting the X-axis resolution.
+.IP \fB\-X\ \fIduration\fR
+Sets the X-axis resolution such that audio with the given
+.I duration
+([[HH:]MM:]SS) fits the maximum X-axis width. For example,
+.EX
+ sox my.mp3 -n remix - spectrogram -X 03:24
+.EE
+or, with Bourne shell, PowerShell, etc.,
+.EX
+ sox my.mp3 -n remix - spectrogram -X $(soxi -D my.mp3)
+.EE
+.SP
+See also
+.B \-x
+for an alternative way of setting the X-axis resolution.
.IP \fB\-y\ \fInum\fR
Y-axis resolution (1 \- 4), default 2.
This controls the height of the spectrogram;
--- a/src/spectrogram.c
+++ b/src/spectrogram.c
@@ -79,6 +79,8 @@
static int getopts(sox_effect_t * effp, int argc, char **argv)
{priv_t * p = (priv_t *)effp->priv;
+ size_t duration_1e5;
+ char const * next;
int c;
assert(array_length(p->bit_rev_table) >= (size_t)dft_br_len(MAX_DFT_SIZE));
@@ -87,7 +89,7 @@
p->spectrum_points = 249, p->perm = 1;
p->out_name = "spectrogram.png", p->comment = "Created by SoX";
- while ((c = getopt(argc, argv, "+x:y:z:Z:q:p:w:st:c:amlho:")) != -1) switch (c) {+ while ((c = getopt(argc, argv, "+x:X:y:z:Z:q:p:w:st:c:amlho:")) != -1) switch (c) { GETOPT_NUMERIC('x', pixels_per_sec, 1 , 5000) GETOPT_NUMERIC('y', y_size , 1 , 1 + MAX_DFT_SIZE_SHIFT) GETOPT_NUMERIC('z', dB_range , 20 , 180)@@ -96,6 +98,12 @@
GETOPT_NUMERIC('p', perm , 1 , 6)case 'w': p->win_type = lsx_enum_option(c, window_options); break;
case 's': p->slack_overlap = sox_true; break;
+ case 'X':
+ next = lsx_parsesamples(1e5, optarg, &duration_1e5, 't');
+ if (next == NULL || *next != '\0')
+ return lsx_usage(effp);
+ p->pixels_per_sec = MAX_COLS * 1e5 / duration_1e5;
+ break;
case 't': p->title = optarg; break;
case 'c': p->comment = optarg; break;
case 'a': p->no_axes = sox_true; break;
@@ -497,7 +505,8 @@
"spectrogram", 0, SOX_EFF_MODIFY, getopts, start, flow, drain, stop, 0, sizeof(priv_t)};
static char const * lines[] = {"[options]",
- "\t-x num\tX-axis pixels/second, default 100",
+ "\t-x num\tX-axis pixels/second, default 100. -x & -X are alternatives",
+ "\t-X time\tAudio duration to fit to X-axis e.g. $(soxi -D file)",
"\t-y num\tY-axis resolution (1 - 4), default 2",
"\t-z num\tZ-axis range in dB, default 120",
"\t-Z num\tZ-axis maximum in dBFS, default 0",