Spoken word recognizer is a project given by instructor within the course. The general outline of the project is about training the computer voice input to understand English words (i.e. digits) through Python.
The program is coded in Python 2.7. We highly recommend using virtualenv to install and run the program without any issue. virtualenv is a tool to create isolated Python environment. By using it, you can avoid any interference that might be a problem because of your previous Python packages.
ad3==2.2.1
cycler==0.10.0
Cython==0.29.7
hmmlearn==0.2.0
matplotlib==1.5.1
neurolab==0.3.5
numpy==1.10.2
pandas==0.21.1
PyAudio==0.2.11
pyparsing==2.4.0
pystruct==0.2.4
python-dateutil==2.8.0
python-speech-features==0.6
pytz==2019.1
scikit-learn==0.16.1
scipy==0.17.1
six==1.12.0
SpeechRecognition==3.8.1
pip install -r requirements.txt --ignore-requires-python
Then, to run:
python record.py
#TODO: Explain how to run
- Free Spoken Digit Dataset (FSDD) - A simple audio/speech dataset consisting of recordings of spoken digits in wav files