/Improving-Numeric-ASR-via-Cues

Code and datasets for paper "Improving Alphanumeric Automatic Speech Recognition Via Cues"

Primary LanguagePython

Improving Numeric ASR via Cues

Synthetic Dataset

  1. Install Coqui-TTS.
  2. Edit Line 24 of this script and set it to the python executable in which the Coqui-TTS is installed.
  3. Run python3 generate_synthetic_data/generate_audio.py. This will dump audio to dump/alphanumeric and dump/numeric.

Code for Experiments

This will be released in the future.