The recorded sound of one note creates several start periods

Question

I use the Librosa library to determine pitch and appearance. In particular, I use and . onset_detect piptrack

This is my code:

def detect_pitch(y, sr, onset_offset=5, fmin=75, fmax=1400):
  y = highpass_filter(y, sr)

  onset_frames = librosa.onset.onset_detect(y=y, sr=sr)
  pitches, magnitudes = librosa.piptrack(y=y, sr=sr, fmin=fmin, fmax=fmax)

  notes = []

  for i in range(0, len(onset_frames)):
    onset = onset_frames[i] + onset_offset
    index = magnitudes[:, onset].argmax()
    pitch = pitches[index, onset]
    if (pitch != 0):
      notes.append(librosa.hz_to_note(pitch))

  return notes

def highpass_filter(y, sr):
  filter_stop_freq = 70  # Hz
  filter_pass_freq = 100  # Hz
  filter_order = 1001

  # High-pass filter
  nyquist_rate = sr / 2.
  desired = (0, 0, 1, 1)
  bands = (0, filter_stop_freq, filter_pass_freq, nyquist_rate)
  filter_coefs = signal.firls(filter_order, bands, desired, nyq=nyquist_rate)

  # Apply high-pass filter
  filtered_audio = signal.filtfilt(filter_coefs, [1], y)
  return filtered_audio

When I run this sample on a guitar recorded in the studio, so samples without noise (like this one ), I get very good results in both functions. The start time is correct, and the frequencies are almost always correct (sometimes with some octave errors).

, , . , . onset_detect , . . , .

. - B3, , - E2.

3 ( ). 7 , , 7 1! , - .

, B3, C4, D4, E4:

, , ( ).

, , . , , ? , .

Answer 1

, .

-, , , , , , , , . , , , pianissimo , fortissimo. , , - , pianissimo.

, 2200 ( 0,1 ) , , . , , . , ( 3000), - , 0,1 . 2240 , "" ( , , , , , , ​​ , ).

, , . , , . : . 3 , , , RMS, , , . , , , RMS , "".

script :

import librosa
import numpy as np
import matplotlib.pyplot as plt

# I played around with this but ultimately kept the default value
hoplen=512

y, sr = librosa.core.load("./Vocaroo_s07Dx8dWGAR0.mp3")
# Note that the first ~2240 samples (0.1 seconds) are anomalously low noise,
# so cut out this section from processing
start = 2240
y = y[start:]
idx = np.arange(len(y))

# Calcualte the onset frames in the usual way
onset_frames = librosa.onset.onset_detect(y=y, sr=sr, hop_length=hoplen)
onstm = librosa.frames_to_time(onset_frames, sr=sr, hop_length=hoplen)

# Calculate RMS energy per frame.  I shortened the frame length from the
# default value in order to avoid ending up with too much smoothing
rmse = librosa.feature.rmse(y=y, frame_length=512, hop_length=hoplen)[0,]
envtm = librosa.frames_to_time(np.arange(len(rmse)), sr=sr, hop_length=hoplen)
# Use final 3 seconds of recording in order to estimate median noise level
# and typical variation
noiseidx = [envtm > envtm[-1] - 3.0]
noisemedian = np.percentile(rmse[noiseidx], 50)
sigma = np.percentile(rmse[noiseidx], 84.1) - noisemedian
# Set the minimum RMS energy threshold that is needed in order to declare
# an "onset" event to be equal to 5 sigma above the median
threshold = noisemedian + 5*sigma
threshidx = [rmse > threshold]
# Choose the corrected onset times as only those which meet the RMS energy
# minimum threshold requirement
correctedonstm = onstm[[tm in envtm[threshidx] for tm in onstm]]

# Print both in units of actual time (seconds) and sample ID number
print(correctedonstm+start/sr)
print(correctedonstm*sr+start)

fg = plt.figure(figsize=[12, 8])

# Print the waveform together with onset times superimposed in red
ax1 = fg.add_subplot(2,1,1)
ax1.plot(idx+start, y)
for ii in correctedonstm*sr+start:
    ax1.axvline(ii, color='r')
ax1.set_ylabel('Amplitude', fontsize=16)

# Print the RMSE together with onset times superimposed in red
ax2 = fg.add_subplot(2,1,2, sharex=ax1)
ax2.plot(envtm*sr+start, rmse)
for ii in correctedonstm*sr+start:
    ax2.axvline(ii, color='r')
# Plot threshold value superimposed as a black dotted line
ax2.axhline(threshold, linestyle=':', color='k')
ax2.set_ylabel("RMSE", fontsize=16)
ax2.set_xlabel("Sample Number", fontsize=16)

fg.show()

:

In [1]: %run rosatest
[ 0.17124717  1.88952381  3.74712018  5.62793651]
[   3776.   41664.   82624.  124096.]

, , :

Answer 2

, ?

onset_detect , optionals, ?

, optionals (, , ):

• librosa.util.peak_pick (, )
• backtrack

. , :

def detect_pitch(y, sr, onset_offset=5, fmin=75, fmax=1400):
  y = highpass_filter(y, sr)

  o_env = librosa.onset.onset_strength(y, sr=sr)
  times = librosa.frames_to_time(np.arange(len(o_env)), sr=sr)

  onset_frames = librosa.onset.onset_detect(y=o_env, sr=sr)
  pitches, magnitudes = librosa.piptrack(y=y, sr=sr, fmin=fmin, fmax=fmax)

  notes = []

  for i in range(0, len(onset_frames)):
    onset = onset_frames[i] + onset_offset
    index = magnitudes[:, onset].argmax()
    pitch = pitches[index, onset]
    if (pitch != 0):
      notes.append(librosa.hz_to_note(pitch))

  return notes

def highpass_filter(y, sr):
  filter_stop_freq = 70  # Hz
  filter_pass_freq = 100  # Hz
  filter_order = 1001

  # High-pass filter
  nyquist_rate = sr / 2.
  desired = (0, 0, 1, 1)
  bands = (0, filter_stop_freq, filter_pass_freq, nyquist_rate)
  filter_coefs = signal.firls(filter_order, bands, desired, nyq=nyquist_rate)

  # Apply high-pass filter
  filtered_audio = signal.filtfilt(filter_coefs, [1], y)
  return filtered_audio

?