{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"This notebook computes the average SNR a given Voice Dataset. If the SNR is too low, that might reduce the performance or prevent model to learn.\n",
"\n",
"To use this notebook, you need:\n",
"- WADA SNR estimation: http://www.cs.cmu.edu/~robust/archive/algorithms/WADA_SNR_IS_2008/\n",
"- FFMPEG: ```sudo apt-get install ffmpeg ``` \n"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import os, sys\n",
"import glob\n",
"import subprocess\n",
"import tempfile\n",
"import IPython\n",
"import soundfile as sf\n",
"import numpy as np\n",
"from tqdm import tqdm\n",
"from multiprocessing import Pool"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"# Set the meta parameters\n",
"DATA_PATH = \"/home/erogol/Data/m-ai-labs/de_DE/by_book/female/eva_k/\"\n",
"NUM_PROC = 1\n",
"CURRENT_PATH = os.getcwd()"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"def compute_file_snr(file_path):\n",
" \"\"\" Convert given file to required format with FFMPEG\n",
" and process with WADA\n",
" \"\"\"\n",
" _, sr = sf.read(file_path)\n",
" new_file = file_path.replace(\".wav\", \"_tmp.wav\")\n",
" if sr != 16000:\n",
" command = 'ffmpeg -i \"{}\" -ac 1 -acodec pcm_s16le -y -ar {} \"{}\"'.format(file_path, 16000, new_file)\n",
" else:\n",
" command = f'cp {file_path} {new_file}'\n",
" os.system(command)\n",
" command = [f\"{CURRENT_PATH}/WadaSNR/Exe/WADASNR\", f'-i {new_file}', f'-t {CURRENT_PATH}/WadaSNR/Exe/Alpha0.400000.txt', '-ifmt mswav']\n",
" pipe = subprocess.Popen(\" \".join(command), shell=True, stdout=subprocess.PIPE).stdout\n",
" output = pipe.read()\n",
" try:\n",
" output = float(output.split()[-3].decode(\"utf-8\"))\n",
" except:\n",
" raise RuntimeError(\" \".join(command))\n",
" os.system(\"rm {}\".format(new_file))\n",
" return output, file_path\n"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"wav_file = \"/home/erogol/Data/LJSpeech-1.1/wavs/LJ001-0001.wav\"\n",
"output = compute_file_snr(wav_file)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" > Number of wav files 13331\n"
]
}
],
"source": [
"wav_files = glob.glob(\"{}/**/*.wav\".format(DATA_PATH), recursive=True)\n",
"print(\" > Number of wav files {}\".format(len(wav_files)))"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"13331it [22:53, 9.71it/s]\n"
]
}
],
"source": [
"if NUM_PROC == 1:\n",
" file_snrs = [None] * len(wav_files) \n",
" for idx, wav_file in tqdm(enumerate(wav_files)):\n",
" tup = compute_file_snr(wav_file)\n",
" file_snrs[idx] = tup\n",
"else:\n",
" with Pool(NUM_PROC) as pool:\n",
" file_snrs = list(tqdm(pool.imap(compute_file_snr, wav_files), total=len(wav_files)))"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" > Average SNR of the dataset:65.62862835473709\n"
]
}
],
"source": [
"snrs = [tup[0] for tup in file_snrs]\n",
"\n",
"error_idxs = np.where(np.isnan(snrs) == True)[0]\n",
"error_files = [file_names[idx] for idx in error_idxs]\n",
"\n",
"file_snrs = [i for j, i in enumerate(file_snrs) if j not in error_idxs]\n",
"file_names = [tup[1] for tup in file_snrs]\n",
"snrs = [tup[0] for tup in file_snrs]\n",
"\n",
"print(\" > Average SNR of the dataset:{}\".format(np.mean(snrs)))"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" > /home/erogol/Data/m-ai-labs/de_DE/by_book/female/eva_k/toten_seelen/wavs/toten_seelen_21_f000011.wav - snr:17.236514\n"
]
},
{
"data": {
"text/html": [
"\n",
" \n",
" "
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" > /home/erogol/Data/m-ai-labs/de_DE/by_book/female/eva_k/toten_seelen/wavs/toten_seelen_19_f000105.wav - snr:17.620196\n"
]
},
{
"data": {
"text/html": [
"\n",
" \n",
" "
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" > /home/erogol/Data/m-ai-labs/de_DE/by_book/female/eva_k/toten_seelen/wavs/toten_seelen_16_f000048.wav - snr:17.771109\n"
]
},
{
"data": {
"text/html": [
"\n",
" \n",
" "
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" > /home/erogol/Data/m-ai-labs/de_DE/by_book/female/eva_k/toten_seelen/wavs/toten_seelen_21_f000084.wav - snr:18.852683\n"
]
},
{
"data": {
"text/html": [
"\n",
" \n",
" "
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" > /home/erogol/Data/m-ai-labs/de_DE/by_book/female/eva_k/werde_die_du_bist/wavs/werde_die_du_bist_04_f000034.wav - snr:19.213945\n"
]
},
{
"data": {
"text/html": [
"\n",
" \n",
" "
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" > /home/erogol/Data/m-ai-labs/de_DE/by_book/female/eva_k/toten_seelen/wavs/toten_seelen_16_f000101.wav - snr:19.526065\n"
]
},
{
"data": {
"text/html": [
"\n",
" \n",
" "
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" > /home/erogol/Data/m-ai-labs/de_DE/by_book/female/eva_k/toten_seelen/wavs/toten_seelen_19_f000229.wav - snr:19.785003\n"
]
},
{
"data": {
"text/html": [
"\n",
" \n",
" "
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" > /home/erogol/Data/m-ai-labs/de_DE/by_book/female/eva_k/werde_die_du_bist/wavs/werde_die_du_bist_04_f000033.wav - snr:19.811579\n"
]
},
{
"data": {
"text/html": [
"\n",
" \n",
" "
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" > /home/erogol/Data/m-ai-labs/de_DE/by_book/female/eva_k/werde_die_du_bist/wavs/werde_die_du_bist_03_f000007.wav - snr:20.052098\n"
]
},
{
"data": {
"text/html": [
"\n",
" \n",
" "
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" > /home/erogol/Data/m-ai-labs/de_DE/by_book/female/eva_k/toten_seelen/wavs/toten_seelen_21_f000031.wav - snr:20.055627\n"
]
},
{
"data": {
"text/html": [
"\n",
" \n",
" "
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# find worse SNR files\n",
"N = 10 # number of files to fetch\n",
"file_idxs = np.argsort(snrs)\n",
"for i in range(N):\n",
" idx = file_idxs[i]\n",
" file_name = file_names[idx]\n",
" wav, sr = sf.read(file_name)\n",
" print(\" > {} - snr:{}\".format(file_name, snrs[idx]))\n",
" IPython.display.display(IPython.display.Audio(wav, rate=sr))"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" > /home/erogol/Data/m-ai-labs/de_DE/by_book/female/eva_k/kleine_lord/wavs/kleine_lord_04_f000156.wav - snr:100.0\n"
]
},
{
"data": {
"text/html": [
"\n",
" \n",
" "
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" > /home/erogol/Data/m-ai-labs/de_DE/by_book/female/eva_k/toten_seelen/wavs/toten_seelen_15_f000107.wav - snr:100.0\n"
]
},
{
"data": {
"text/html": [
"\n",
" \n",
" "
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" > /home/erogol/Data/m-ai-labs/de_DE/by_book/female/eva_k/toten_seelen/wavs/toten_seelen_26_f000133.wav - snr:100.0\n"
]
},
{
"data": {
"text/html": [
"\n",
" \n",
" "
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" > /home/erogol/Data/m-ai-labs/de_DE/by_book/female/eva_k/toten_seelen/wavs/toten_seelen_33_f000102.wav - snr:100.0\n"
]
},
{
"data": {
"text/html": [
"\n",
" \n",
" "
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" > /home/erogol/Data/m-ai-labs/de_DE/by_book/female/eva_k/toten_seelen/wavs/toten_seelen_12_f000200.wav - snr:100.0\n"
]
},
{
"data": {
"text/html": [
"\n",
" \n",
" "
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" > /home/erogol/Data/m-ai-labs/de_DE/by_book/female/eva_k/toten_seelen/wavs/toten_seelen_28_f000193.wav - snr:100.0\n"
]
},
{
"data": {
"text/html": [
"\n",
" \n",
" "
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" > /home/erogol/Data/m-ai-labs/de_DE/by_book/female/eva_k/toten_seelen/wavs/toten_seelen_28_f000048.wav - snr:100.0\n"
]
},
{
"data": {
"text/html": [
"\n",
" \n",
" "
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" > /home/erogol/Data/m-ai-labs/de_DE/by_book/female/eva_k/toten_seelen/wavs/toten_seelen_04_f000145.wav - snr:100.0\n"
]
},
{
"data": {
"text/html": [
"\n",
" \n",
" "
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" > /home/erogol/Data/m-ai-labs/de_DE/by_book/female/eva_k/toten_seelen/wavs/toten_seelen_12_f000006.wav - snr:100.0\n"
]
},
{
"data": {
"text/html": [
"\n",
" \n",
" "
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" > /home/erogol/Data/m-ai-labs/de_DE/by_book/female/eva_k/toten_seelen/wavs/toten_seelen_21_f000108.wav - snr:100.0\n"
]
},
{
"data": {
"text/html": [
"\n",
" \n",
" "
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# find best recordings\n",
"N = 10 # number of files to fetch\n",
"file_idxs = np.argsort(-1 * np.array(snrs))\n",
"for i in range(N):\n",
" idx = file_idxs[i]\n",
" file_name = file_names[idx]\n",
" wav, sr = sf.read(file_name)\n",
" print(\" > {} - snr:{}\".format(file_name, snrs[idx]))\n",
" IPython.display.display(IPython.display.Audio(wav, rate=sr))"
]
}
],
"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": "3.7.2"
}
},
"nbformat": 4,
"nbformat_minor": 2
}