Welcome to ISCA Web ...
HMM-based ASR
ASR based on comparing incoming speech with statistical models for speech units (acoustic models), usually in the context of a language model which deploys statistics about word sequences.
- · Kai-Fu Lee is one of the best-known names in the development of HMM-based ASR. He recorded this lecture in 1993:
- There are two modules in Edinburgh's speech.zone: here and here
- · Hermann Ney: 2012 Review
- · Columbia Speech Recognition course Lectures 3-12
- · Andrew Maas: April 10 and 12 lectures