Explore the latest advancements in AI-powered transcription technology. Achieve faster, more accurate transcripts for audio and video content, streamline workflows, and enhance accessibility.
STT
ASR - A brief history and intro
Automated Speech Recognition (ASR) transcribes voice audio data into text data, that which is consumable and searchable. We go through its history and the current state of the art.
John Jacob
STTNLPLLM
Going beyond Speech-To-Text
We explore what can be achieved beyond searchable transcripts by combining Automated Speech Recognition with Natural Language Processing, Natural Language Understanding and use of Large Language Models.
Johann Verghese