Enhancing speech intelligibility in reverberant spaces by a speech features distributions dependent pre-processing.
Yosra MzahSandra ChaouiMeriem JaïdanePublished in: Int. J. Speech Technol. (2018)
Keyphrases
- speech signal
- speech recognition
- preprocessing
- feature extraction
- speech recognition systems
- cepstral features
- low level
- speech synthesis
- automatic speech recognition
- speech emotion recognition
- lexical features
- audio features
- data mining
- image features
- spectral features
- probability distribution
- recognition engine
- spontaneous speech
- audio visual
- speaker identification
- broadcast news
- vocal tract
- spoken language
- neural network
- endpoint detection
- pattern recognition
- linear predictive coding
- non stationary
- speaker recognition
- text to speech
- co occurrence
- language acquisition
- post processing