SCOOT: Automatic Speech Recognition

Research on Automatic Speech Recognition (ASR) dates back to the 1950s.

See Lecture 1 in the Columbia Speech Recognition course for an introduction.

Preethi Jyothi, IIT Bombay gives a recent overview talk at Microsoft  (2017).

There is an edX online course on Speech Recognition. This is an introductory course to principles of speech recognition, created by Jasha Droppo, Mike Seltzer and Andreas Stolcke as part of Microsoft's "AI School", but really self-contained and not specific to Microsoft AI services.  It's aimed at undergraduatess wishing to learn the basic principles of speech recognition.

Michael Picheny of IBM presents a review of progress in ASR in  Speech Recognition: What's Left?  (2018, I think). Here's Michael's abstract:

Abstract:

Recent speech recognition advances on the SWITCHBOARD corpus suggest that because of recent advances in Deep Learning, we now achieve Word Error Rates comparable to human listeners. Does this mean the speech recognition problem is solved and the community can move on to a different set of problems? In this talk, we examine speech recognition issues that still plague the community and compare and contrast them to what is known about human perception. We specifically highlight issues in accented speech, noisy/reverberant speech, speaking style, rapid adaptation to new domains, and multilingual speech recognition. We try to demonstrate that compared to human perception, there is still much room for improvement, so significant work in speech recognition research is still required from the community.

Hermann Ney (Aachen) provides an excellent tretment of the development of ASR and related Speech Tech over 40 years. This is the ISCA Medalist keynote talk at Interspeech 2021

ASR Methods

• Dynamic Time Warping:  DTW
• Hidden Markov Models HMMs
  
• Neural Nets DNN ASR

ASR Toolkits