Peer-reviewed research
Microphone Distance Adaptation Using Cluster Adaptive Training for Robust Far Field Speech Recognition
Animesh Prasad and Khe Chai Sim, Interspeech 2016, International Speech Communication Association (ISCA), 2016
Read the originalRead on October 16, 2026
- What it is
- A peer-reviewed Interspeech paper that treats the distance between a single microphone and the speaker as a problem for speech recognition. The authors built a corpus by re-recording Wall Street Journal audio at eight distances.
- How much weight it carries
- Peer-reviewed and published at a major speech conference. The paper is about adapting a recognizer to distance, so it does not report a clean word-error-rate curve for each distance.
Facts taken from this source
- Prasad and Sim built a far-field speech corpus by re-recording Wall Street Journal audio with microphones at eight different distances from the source.
“A speech corpus was created by re-recording the Wall Street Journal (WSJ0) audio using far-field microphones with 8 different distances from the source.” (Abstract)