Skip to main content
Signal Processing

Return to Answer

added 44 characters in body
Source Link
MrHat
MrHat
  • 181
  • 1
  • 7

Ok so here is what I found. The distance is dependent on the way that the mfccs are calculated. This makes sense to me and also explains why cepstral mean normalization affects the values of the MCD.

I found this implementation (https://github.com/MattShannon/mcd), which unfortunately did not support .wav files. I ran this and it gives results that are in the correct range for its test examples. I looked into the code and found that the the difference was not so much in the calculation of the MCD (which is straight forward) but rather the mfccs. The library I was using gave mfccs at a different scale (I tried python_speech_features and pyspeech). Using the mfccs from Matlab gave me mfccs in a similar range to that of the repo so I opted to use those.

A noteworthy point is that the first coefficient is quite large which is why it is ignored in (https://github.com/MattShannon/mcd) so I did the same. There are some artifacts in the speech I synthesise which likely accounts for why my MCD is still above 10 but its still lower than 30 now.

Ok so here is what I found. The distance is dependent on the way that the mfccs are calculated. This makes sense to me and also explains why cepstral mean normalization affects the values of the MCD.

I found this implementation (https://github.com/MattShannon/mcd), which unfortunately did not support .wav files. I ran this and it gives results that are in the correct range for its test examples. I looked into the code and found that the the difference was not so much in the calculation of the MCD (which is straight forward) but rather the mfccs. The library I was using gave mfccs at a different scale (I tried python_speech_features and pyspeech). Using the mfccs from Matlab gave me mfccs in a similar range.

A noteworthy point is that the first coefficient is quite large which is why it is ignored in (https://github.com/MattShannon/mcd) so I did the same. There are some artifacts in the speech I synthesise which likely accounts for why my MCD is still above 10 but its still lower than 30 now.

Ok so here is what I found. The distance is dependent on the way that the mfccs are calculated. This makes sense to me and also explains why cepstral mean normalization affects the values of the MCD.

I found this implementation (https://github.com/MattShannon/mcd), which unfortunately did not support .wav files. I ran this and it gives results that are in the correct range for its test examples. I looked into the code and found that the the difference was not so much in the calculation of the MCD (which is straight forward) but rather the mfccs. The library I was using gave mfccs at a different scale (I tried python_speech_features and pyspeech). Using the mfccs from Matlab gave me mfccs in a similar range to that of the repo so I opted to use those.

A noteworthy point is that the first coefficient is quite large which is why it is ignored in (https://github.com/MattShannon/mcd) so I did the same. There are some artifacts in the speech I synthesise which likely accounts for why my MCD is still above 10 but its still lower than 30 now.

Source Link
MrHat
MrHat
  • 181
  • 1
  • 7

Ok so here is what I found. The distance is dependent on the way that the mfccs are calculated. This makes sense to me and also explains why cepstral mean normalization affects the values of the MCD.

I found this implementation (https://github.com/MattShannon/mcd), which unfortunately did not support .wav files. I ran this and it gives results that are in the correct range for its test examples. I looked into the code and found that the the difference was not so much in the calculation of the MCD (which is straight forward) but rather the mfccs. The library I was using gave mfccs at a different scale (I tried python_speech_features and pyspeech). Using the mfccs from Matlab gave me mfccs in a similar range.

A noteworthy point is that the first coefficient is quite large which is why it is ignored in (https://github.com/MattShannon/mcd) so I did the same. There are some artifacts in the speech I synthesise which likely accounts for why my MCD is still above 10 but its still lower than 30 now.