Learn More
  • Thom Blum
  • 2008
Efforts to automatically extract salient features from rich media documents (audio, video, still images, speech, etc.) have been underway and maturing for the last 15 to 20 years; longer than that if you consider speech recognition research. However, there is still a paucity of real world applications that leverage the technology, and scaling the technology(More)
  • 1