On Cross-Corpus Generalization of Deep Learning Based Speech Enhancement.
Ashutosh PandeyDeLiang WangPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2020)
Keyphrases
- deep learning
- speech enhancement
- noise reduction
- noisy environments
- unsupervised learning
- signal to noise ratio
- single channel
- speech signal
- machine learning
- weakly supervised
- mental models
- linear prediction
- vocal tract
- multiscale
- speech recognition
- background noise
- information retrieval
- markov random field
- semi supervised
- hidden markov models
- wiener filter