Welcome! This is the project AutoViDevSpeech, and we are waiting for you!
Many artificial intelligence (AI) researchers draw important insights from developmental science. Conversely, relatively few developmental researchers use AI and speech recognition tools to facilitate the study of behavioral development. Most developmental researchers lack expertise in AI and speech recognition, so the enormous potential of AI and speech recognition to speed progress in video-based developmental research remains untapped. The current project this notable gap by using state-of-the-art algorithm to transcribe videos of developmental research automatically. This tool is part of AutoViDev—an automatic video-analysis tool that uses machine learning to support video-based developmental research.
- Python 3.6
- ffmeg package
- SpeechRecognition Package
- Any API here:
- CMU
- Google Speech Recognition
- Google Cloud Speech API
- Wit.ai
- Microsoft Bing Voice Recognition
- Houndify API
- IBM Speech to Text