Speech separation based on improved deep neural networks with dual outputs of speech features for both target and interfering speakers.
Yanhui TuJun DuYong XuLi-Rong DaiChin-Hui LeePublished in: ISCSLP (2014)
Keyphrases
- speech recognition
- neural network
- speech synthesis
- lexical features
- speech signal
- speech recognition systems
- automatic speech recognition
- spectral features
- speech emotion recognition
- speech recognizer
- pattern recognition
- audio visual
- artificial neural networks
- speaker dependent
- feature set
- low level
- spoken language
- text to speech
- cepstral features
- image features
- neural network model
- speaker recognition
- broadcast news
- feature values
- speaker identification
- classification accuracy
- fuzzy logic
- visual speech
- mel frequency cepstral coefficients
- feature vectors
- back propagation
- multi layer
- feature space
- multilayer perceptron