Two-Stage Neural Network for ICASSP 2023 Speech Signal Improvement Challenge.
Mingshuai LiuShubo LvZihan ZhangRunduo HanXiang HaoXianjun XiaLi ChenYijian XiaoLei XiePublished in: ICASSP (2023)
Keyphrases
- speech signal
- neural network
- speech recognition
- automatic speech recognition
- vocal tract
- noisy environments
- linear prediction
- non stationary
- speaker identification
- spectral analysis
- automatic speech recognition systems
- speaker recognition
- background noise
- hidden markov models
- acoustic features
- pattern recognition
- fundamental frequency
- feature space
- speech quality
- noisy images
- gaussian mixture model
- cepstral coefficients
- computer vision