A Supervised Learning Approach to Monaural Segregation of Reverberant Speech.
Zhaozhang JinDeLiang WangPublished in: IEEE Trans. Speech Audio Process. (2009)
Keyphrases
- speech signal
- supervised learning
- speech recognition
- automatic speech recognition
- vocal tract
- speaker identification
- linear prediction
- automatic speech recognition systems
- reinforcement learning
- unsupervised learning
- noisy environments
- supervised classification
- active learning
- training data
- training set
- semi supervised learning
- learning tasks
- semi supervised
- hidden markov models
- machine learning
- training examples
- non stationary
- speech synthesis
- multiple instance learning
- learning algorithm
- learning problems
- data sets
- text to speech
- neural network
- spoken language
- audio visual
- statistical learning
- unlabeled data
- supervised machine learning
- speaker recognition
- multi stream
- pairwise
- speech recognizer
- pattern recognition
- fundamental frequency
- multimedia
- formant frequencies