EfficientASR: Speech Recognition Network Compression via Attention Redundancy and Chunk-Level FFN Optimization.
Jianzong WangZiqi LiangXulong ZhangNing ChengJing XiaoPublished in: CoRR (2024)
Keyphrases
- speech recognition
- hidden markov models
- language model
- speech signal
- speech recognition technology
- speaker identification
- pattern recognition
- automatic speech recognition
- speech processing
- speech synthesis
- speech understanding
- speech recognizer
- image compression
- speech recognition systems
- keyword spotting
- noisy environments
- isolated word
- speaker diarization
- bayesian networks
- face recognition
- compression ratio
- feature space
- speaker dependent
- speech recognizers
- neural network