I have a problem you guys may know how to solve: I don't want to know if the person is saying "a" or "e", I want to know if he/she is saying (singing) in A (220Hz), A# (233Hz), B (247Hz), etc.
So: how do I find the frequency in a sound sample? I know how to draw the wave, but I can't find an algorithm to find the frequency.
Thanks,
Ricardo, Brazil.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Anonymous
-
2003-05-14
Voiced speech is excited by a harmonic series, and your problem is to estimate the fundamental frequency of this harmonic series. This is a well-known topic in speech processing, and many algorithms have been used for it. Look in any text on speech processing, or use your favorite web search engine looking for "pitch extraction" or "fundamental frequency extraction" or "... estimation".
One caveat: pitch extraction algorithms are sometimes subject to octave errors, so you need to interpret your results carefully.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
I have a problem you guys may know how to solve: I don't want to know if the person is saying "a" or "e", I want to know if he/she is saying (singing) in A (220Hz), A# (233Hz), B (247Hz), etc.
So: how do I find the frequency in a sound sample? I know how to draw the wave, but I can't find an algorithm to find the frequency.
Thanks,
Ricardo, Brazil.
Voiced speech is excited by a harmonic series, and your problem is to estimate the fundamental frequency of this harmonic series. This is a well-known topic in speech processing, and many algorithms have been used for it. Look in any text on speech processing, or use your favorite web search engine looking for "pitch extraction" or "fundamental frequency extraction" or "... estimation".
One caveat: pitch extraction algorithms are sometimes subject to octave errors, so you need to interpret your results carefully.