Merge pull request #42 from jsingh811/new-features

New features

README.md

@@ -205,6 +205,44 @@ convert_files_to_wav(dir_path, audio_format="mp4")
 
 ```
 
+
+## Audio cleaning
+
+To remove low-activity regions from your audio clip, the following sample usage can be referred to.
+
+```
+from pyAudioProcessing import clean
+
+clean.remove_silence(
+	      <path to wav file>,
+               output_file=<path where you want to store cleaned wav file>
+)
+```
+
+## Audio visualization
+
+To see time-domain view of the audios, and the spectrogram of the audios, please refer to the following sample usage.
+
+```
+from pyAudioProcessing import plot
+
+# spectrogram plot
+plot.spectrogram(
+     <path to wav file>,
+    show=True, # set to False if you do not want the plot to show
+    save_to_disk=True, # set to False if you do not want the plot to save
+    output_file=<path where you want to store spectrogram as a png>
+)
+
+# time-series plot
+plot.time(
+     <path to wav file>,
+    show=True, # set to False if you do not want the plot to show
+    save_to_disk=True, # set to False if you do not want the plot to save
+    output_file=<path where you want to store the plot as a png>
+)
+```
+
 ## Author  
 
 Jyotika Singh  

pyAudioProcessing/clean.py

@@ -0,0 +1,45 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Thu Jun 10 15:23:55 2021
+
+@author: jsingh
+"""
+# Imports
+import os
+import numpy
+from scipy.io import wavfile
+from pyAudioProcessing.utils import read_audio
+
+# Globals
+LOW_PT_THRESHOLD = 0.01
+
+# Functions
+
+def remove_silence(
+    input_file, output_file="without_sil.wav", thr=LOW_PT_THRESHOLD
+):
+    """
+    Remove silences from input audio file.
+    """
+    sampling_rate, signal = read_audio(input_file)
+    signal = numpy.array(
+        [
+            list(i)
+            for i in signal
+            if not numpy.all((i == 0))
+        ]
+    )
+    mean_signal = [numpy.mean(list(i)) for i in signal]
+    thrs_p = thr * max(mean_signal)
+    thrs_n = thr * min(mean_signal)
+    signal = numpy.array(
+        [
+            list(i)
+            for i in signal
+            if numpy.all((i > thrs_p)) or numpy.all((i < thrs_n))
+        ]
+    )
+    wavfile.write(output_file, sampling_rate, signal)
+
+