Identifying surgical-mask speech using deep neural networks on low-level aggregation.
Xinzhou XuJun DengZixing ZhangChen WuBjörn W. SchullerPublished in: SAC (2021)
Keyphrases
- low level
- neural network
- high level
- higher level
- artificial neural networks
- fuzzy logic
- speech recognition
- genetic algorithm
- neural network model
- data aggregation
- visual cues
- speech synthesis
- pattern recognition
- lower level
- intraoperative
- fuzzy systems
- rank aggregation
- recurrent neural networks
- audio features
- mid level
- automatic speech recognition
- speech signal
- audio visual
- operating room
- low level features
- visual information
- back propagation
- visual features
- recognition engine
- multi layer
- learning algorithm
- multi modal
- text to speech
- broadcast news
- x ray
- minimally invasive
- image guided
- fault diagnosis
- self organizing maps
- computer assisted
- multilayer perceptron
- training process