Weighted MTF for predicting speech intelligibility in reverberant sound fields.
Hiroyuki MiyataTammo HoutgastPublished in: EUROSPEECH (1991)
Keyphrases
- speech signal
- speech recognition
- automatic speech recognition systems
- sound source
- acoustic features
- automatic speech recognition
- linear prediction
- vocal tract
- speech processing
- speech synthesis
- computer vision
- speaker identification
- pattern recognition
- data sets
- fundamental frequency
- noisy environments
- language model
- hidden markov models
- data mining
- signal to noise ratio
- non stationary
- weighted sum
- audio visual
- english text
- multiscale
- recognition engine
- image processing
- feature selection