src/postprocessor/vad.py

#! /usr/bin/env python
# encoding: utf-8
'''
MIT License

Copyright (c) 2018 Mauricio

Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:

The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.

Adapted from https://github.com/mauriciovander/silence-removal/blob/master/vad.py
'''
import numpy

class VoiceActivityDetection:

    def __init__(self):
        self.__step = 160
        self.__buffer_size = 160 
        self.__buffer = numpy.array([],dtype=numpy.int16)
        self.__out_buffer = numpy.array([],dtype=numpy.int16)
        self.__n = 0
        self.__VADthd = 0.
        self.__VADn = 0.
        self.__silence_counter = 0

    # Voice Activity Detection
    # Adaptive threshold
    def vad(self, _frame, sc_threshold=20):
        frame = numpy.array(_frame) ** 2.
        result = True
        threshold = 0.2
        thd = numpy.min(frame) + numpy.ptp(frame) * threshold
        self.__VADthd = (self.__VADn * self.__VADthd + thd) / float(self.__VADn + 1.)
        self.__VADn += 1.

        if numpy.mean(frame) <= self.__VADthd:
            self.__silence_counter += 1
        else:
            self.__silence_counter = 0
        if self.__silence_counter > sc_threshold:
            result = False
        return result

    # Push new audio samples into the buffer.
    def add_samples(self, data):
        self.__buffer = numpy.append(self.__buffer, data)
        result = len(self.__buffer) >= self.__buffer_size
        # print('__buffer size %i'%self.__buffer.size)
        return result

    # Pull a portion of the buffer to process
    # (pulled samples are deleted after being
    # processed
    def get_frame(self):
        window = self.__buffer[:self.__buffer_size]
        self.__buffer = self.__buffer[self.__step:]
        # print('__buffer size %i'%self.__buffer.size)
        return window

    # Adds new audio samples to the internal
    # buffer and process them
    def process(self, data, sc_threshold):
        self.__buffer = numpy.array([],dtype=numpy.int16)
        self.__out_buffer = numpy.array([],dtype=numpy.int16)
        if self.add_samples(data):
            while len(self.__buffer) >= self.__buffer_size:
                # Framing
                window = self.get_frame()
                if self.vad(window, sc_threshold):  # speech frame
                	self.__out_buffer = numpy.append(self.__out_buffer, window)
        return self.__out_buffer