Noise-Immune Multisensor Transduction of Speech.
Abstract
Two types of configurations of multiple sensors were developed, tested and evaluated in speech recognition application for robust performance in high levels of acoustic background noise: One type combines the individual sensor signals to provide a single speech signal input, and the other provides several parallel inputs. For single-input systems, several configurations of multiple sensors were developed and tested. Results from formal speech intelligibility and quality tests in simulated fighter aircraft cockpit noise show that each of the two-sensor configurations tested outperforms the constituent individual sensors in high noise. Also presented are results comparing the performance of two-sensor configurations and individual sensors in speaker-dependent, isolated-word speech recognition tests performed using a commercial recognizer (Verbex 4000) in simulated fighter aircraft cockpit noise. Keywords include: Multisensor transduction, Noise Reduction, Speech Enhancement, and Speech Recognition Testing, in Noise.
Document Details
- Document Type
- Technical Report
- Publication Date
- Aug 01, 1986
- Accession Number
- ADA174693
Entities
People
- Alan Derr
- Claudia M. Henry
- Richard M. Schwartz
- Salim Roucos
- Vishu R. Viswanathan
Organizations
- BBN Technologies