Branchformer: Parallel MLP-Attention Architectures to Capture Local and Global Context for Speech Recognition and Understanding.
Yifan PengSiddharth DalmiaIan R. LaneShinji WatanabePublished in: ICML (2022)
Keyphrases
- speech recognition
- global context
- language model
- hidden markov models
- automatic speech recognition
- global information
- speech recognition technology
- speech synthesis
- pattern recognition
- neural network
- multilayer perceptron
- speaker identification
- speech recognizer
- named entities
- speech signal
- speech recognition systems
- speaker independent
- keywords
- sift descriptors
- noisy environments
- n gram
- visual features
- feature extraction
- image segmentation
- artificial intelligence
- data mining