{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "transparent-mattress",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Populating the interactive namespace from numpy and matplotlib\n"
]
}
],
"source": [
"%pylab inline"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "otherwise-calvin",
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"import sys\n",
"sys.path.insert(0, \"/home/georg/tools/noise_reduction\")\n",
"os.environ['CUDA_VISIBLE_DEVICES'] = \"\""
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "twenty-fraud",
"metadata": {},
"outputs": [],
"source": [
"import re\n",
"import pandas as pd\n",
"import numpy as np\n",
"import librosa\n",
"from scipy.io import wavfile\n",
"import librosa.display\n",
"from pydub import AudioSegment\n",
"from IPython.display import display_html\n",
"import torch\n",
"\n",
"\n",
"def _convert_array(arr, force_int=False, force_float=False):\n",
" if isinstance(arr, torch.Tensor):\n",
" arr = arr.cpu().detach().numpy()\n",
" assert(len(arr.shape) in (1, 2))\n",
" if len(arr.shape) == 2:\n",
" assert(arr.shape[0] == 1)\n",
" arr = arr[0]\n",
" if force_int and \"float\" in str(arr.dtype):\n",
" arr = np.floor(arr.copy() * 32768).astype(np.int16)\n",
" if force_float and \"int\" in str(arr.dtype):\n",
" arr = arr.copy().astype(np.float32) / 32768\n",
" return arr\n",
"\n",
"\n",
"def plot_ft(arr, window_size=1024, hop_length=512, n_mels=128):\n",
" arr = _convert_array(arr, force_float=True)\n",
" window = np.hanning(window_size)\n",
" stft= librosa.core.spectrum.stft(arr, n_fft=window_size, hop_length=hop_length, window=window)\n",
" out = 2 * np.abs(stft) / np.sum(window)\n",
" data = librosa.amplitude_to_db(out, ref=np.max)\n",
"\n",
" plt.figure(figsize=(16, 10))\n",
" librosa.display.specshow(data, x_axis='time', y_axis='mel', sr=16000)\n",
" plt.set_cmap('afmhot')\n",
"\n",
"\n",
"def play_array(arr):\n",
" arr = _convert_array(arr, force_int=True)\n",
" display_html(AudioSegment(\n",
" arr.tobytes(), \n",
" frame_rate=16000,\n",
" sample_width=2, \n",
" channels=1\n",
" ))"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "practical-mississippi",
"metadata": {},
"outputs": [],
"source": [
"import noisereduce as nr"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "elementary-knife",
"metadata": {},
"outputs": [],
"source": [
"_, easy_arr = wavfile.read(\"tmp/phone_align.wav\")"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "parliamentary-peripheral",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
" \n",
" "
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"play_array(easy_arr)"
]
},
{
"cell_type": "code",
"execution_count": 21,
"id": "acceptable-tucson",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
" \n",
" "
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"out = nr.reduce_noise(y=easy_arr, sr=16000, stationary=False, prop_decrease=0.95)\n",
"play_array(out * 2)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "southeast-provider",
"metadata": {},
"outputs": [],
"source": [
"_, hard_arr = wavfile.read(\"tmp/bg_noisy.wav\")"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "focused-stereo",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
" \n",
" "
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"play_array(hard_arr)"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "incredible-arbor",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
" \n",
" "
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"out = nr.reduce_noise(y=hard_arr, sr=16000, stationary=False, prop_decrease=1.0)\n",
"play_array(out * 2)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "generous-scotland",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "friendly-bankruptcy",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "cosmetic-madrid",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.12"
}
},
"nbformat": 4,
"nbformat_minor": 5
}