We’re rewarding the question askers & reputations are being recalculated! Read more.
Search type Search syntax
Tags [tag]
Exact "words here"
Author user:1234
user:me (yours)
Score score:3 (3+)
score:0 (none)
Answers answers:3 (3+)
answers:0 (none)
isaccepted:yes
hasaccepted:no
inquestion:1234
Views views:250
Sections title:apples
body:"apples oranges"
URL url:"*.example.com"
Favorites infavorites:mine
infavorites:1234
Status closed:yes
duplicate:no
migrated:no
wiki:no
Types is:question
is:answer
Exclude -[tag]
-apples
For more details on advanced search visit our help page
Results tagged with Search options answers only user 154

Speech processing is the study of speech signals and the processing methods of these signals.

1
vote
Your code appears to be looking for zero crossings of the rectified signal, which won’t work reliably if your signal has strong harmonics or overtones of the fundamental frequency within your filter’s …
answered Feb 17 '18 by hotpaw2
1
vote
Percent overlap merely sets how often you measure the energy, relative to the window width. You can re-measure every sample, or once per annum, or any density in between.
answered Mar 9 '14 by hotpaw2
3
votes
It's common, when computing a cepstrum, to replace any zero's or tiny magnitudes in the 1st FFT result with some (noise) floor value to keep the scale and range of the log function "reasonable looking …
answered Jan 20 '14 by hotpaw2
0
votes
The second artifact can be caused by the fact that phase vocoder slow-down resynthesis can reduce the frequency of any natural tremolo and vibrato in the human speaking voice, as well as any tiny peri …
answered Feb 21 by hotpaw2
0
votes
Each frame to be FFT’d needs to be individually windowed to avoid rectangular window artifacts (sometimes called “leakage”) due to the finite length of the FFT. The frame length you choose depends on …
answered May 11 '18 by hotpaw2
0
votes
If we have a finite window of real world data, but wish to apply mathematical concepts which seem to require signals that are infinite in length or duration, many other assumptions are often applied. …
answered Jan 29 by hotpaw2
1
vote
There is a massive range of possible sounds that a human might recognize (or mis-recognize) as the same word in their language. The problem is searching a large dimensional space representing all tho …
answered Dec 27 '13 by hotpaw2
1
vote
If the process that creates a spectrogram includes the use of a windowing function, then the artifacts of that windowing will have a nonzero bandwidth associated with that particular window function ( …
answered Jul 8 '15 by hotpaw2
0
votes
You have to time stamp the speech with something that did not exist in the past. For instance, generate a cryptographic random number, and compare the spoken response latency to the speed of light ov …
answered Aug 31 by hotpaw2
1
vote
The sample rate divided by the frame rate will give you the window shift in samples. The ratio of the window (length - shift) to the window length will give you an overlap factor. The sample rate di …
answered Sep 28 '13 by hotpaw2
0
votes
Octave jumps down can occur if there is more noise (or other modulation) around a sub-harmonic of the pitch frequency, than at pitch. Octave jumps upwards can occur if the timbre contains strong over …
answered May 12 '18 by hotpaw2
0
votes
You might try padding the shorter (and even the longer) speech samples with a wide range of different (but realistic) background noise environments to create a larger training set (all to an equal tra …
answered Oct 8 '17 by hotpaw2
3
votes
Tapering the two ends of a short audio signal allows it to be played at an arbitrary time after and before silence without a speaker "pop" or loud click. Using a raised cosine taper reduces potential …
answered May 14 '14 by hotpaw2
6
votes
More overlap means you end up with more windows (of a given length) per second of audio. More windows (of a given length) requires more FFTs which requires more MACs or FLOPs which generally requires …
answered Dec 27 '16 by hotpaw2