Spotting Keywords in Audio and Video Files

United States call centers generate more than a billion hours of audio recordings every year and less than 25% of the audio is made searchable or analyzed.

Launching out of Y Combinator’s Winter 2016 class, DeepGram uses deep learning and GPUs hosted in the Amazon Web Services cloud to quickly index audio and make it searchable.

The free demo on the DeepGram site allows you to upload or provide a URL for an audio file, enter a keyword or phrase, and quickly analyze the audio to highlight precisely all the places your keyword is mentioned.

Below is the result – the red mark indicates where ‘NVIDIA’ is mentioned in a recent Share Your Science interview with Jeroen Tromp of Princeton.

Spotting Keywords in Audio Files with GPUs

The Y Combinator blog post outlines how speech search is motivated by market factors. There has been a structural change in phone support from on-site employees to a distributed, international workforce which makes quality assurance more challenging. Businesses are also focusing more on data and analytics, and they want actionable insights from their information-rich audio datasets.


About Brad Nemire

Brad Nemire
Brad Nemire is on the Developer Marketing team and loves reading about all of the fascinating research being done by developers using NVIDIA GPUs. Reach out to Brad on Twitter @BradNemire and let him know how you’re using GPUs to accelerate your research. Brad graduated from San Diego State University and currently resides in San Jose, CA. Follow @BradNemire on Twitter
  • disqus_5T2jXBEN10

    New and improved Echelon System combine this with amssively parraleled computers or maybe quantum computers and you have some seriously creepy paradigms