init

Author: Tony607

.gitignore

@@ -0,0 +1,87 @@
+### https://raw.github.com/github/gitignore/f57304e9762876ae4c9b02867ed0cb887316387e/Python.gitignore
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+env/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*,cover
+.hypothesis/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# dotenv
+.env
+
+# virtualenv
+.venv
+venv/
+ENV/
+
+# Spyder project settings
+.spyderproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+/.idea/
+
+/checkpoints/
+.DS_Store
+
+XY_dev/
+XY_train/
+*.npy

README.md

@@ -0,0 +1,6 @@
+numpy
+keras
+h5py
+pydub
+scipy
+matplotlib

Trigger word detection - v1.ipynb

@@ -0,0 +1,46 @@
+import matplotlib.pyplot as plt
+from scipy.io import wavfile
+import os
+from pydub import AudioSegment
+
+# Calculate and plot spectrogram for a wav audio file
+def graph_spectrogram(wav_file):
+    rate, data = get_wav_info(wav_file)
+    nfft = 200 # Length of each window segment
+    fs = 8000 # Sampling frequencies
+    noverlap = 120 # Overlap between windows
+    nchannels = data.ndim
+    if nchannels == 1:
+        pxx, freqs, bins, im = plt.specgram(data, nfft, fs, noverlap = noverlap)
+    elif nchannels == 2:
+        pxx, freqs, bins, im = plt.specgram(data[:,0], nfft, fs, noverlap = noverlap)
+    return pxx
+
+# Load a wav file
+def get_wav_info(wav_file):
+    rate, data = wavfile.read(wav_file)
+    return rate, data
+
+# Used to standardize volume of audio clip
+def match_target_amplitude(sound, target_dBFS):
+    change_in_dBFS = target_dBFS - sound.dBFS
+    return sound.apply_gain(change_in_dBFS)
+
+# Load raw audio files for speech synthesis
+def load_raw_audio():
+    activates = []
+    backgrounds = []
+    negatives = []
+    for filename in os.listdir("./raw_data/activates"):
+        if filename.endswith("wav"):
+            activate = AudioSegment.from_wav("./raw_data/activates/"+filename)
+            activates.append(activate)
+    for filename in os.listdir("./raw_data/backgrounds"):
+        if filename.endswith("wav"):
+            background = AudioSegment.from_wav("./raw_data/backgrounds/"+filename)
+            backgrounds.append(background)
+    for filename in os.listdir("./raw_data/negatives"):
+        if filename.endswith("wav"):
+            negative = AudioSegment.from_wav("./raw_data/negatives/"+filename)
+            negatives.append(negative)
+    return activates, negatives, backgrounds