A method for predicting the intelligibility of noisy and non-linearly enhanced binaural speech.
Asger Heidemann AndersenJan Mark de HaanZheng-Hua TanJesper JensenPublished in: ICASSP (2016)
Keyphrases
- detection method
- information retrieval
- data sets
- multiscale
- hybrid method
- classification method
- significant improvement
- speech recognition
- experimental evaluation
- error rate
- feature set
- noisy environments
- high precision
- missing data
- synthetic data
- edge detection
- high accuracy
- dynamic programming
- hidden markov models
- prior knowledge
- pattern recognition
- support vector
- image sequences