Cited in
(34)- Beta-order minimum mean-square error multichannel spectral amplitude estimation for speech enhancement
- Progressive learning: a deep learning framework for continual learning
- Bayesian estimation of Dirichlet mixture model with variational inference
- Binaural classification-based speech segregation and robust speaker recognition system
- A study of HMM-based bandwidth extension of speech signals
- A noise-based stabilizer for convolutional neural networks
- Multiple sound source localization and counting using one pair of microphones in noisy and reverberant environments
- Generalized phase space projection for nonlinear noise reduction
- Gated Orthogonal Recurrent Units: On Learning to Forget
- COFFIN
- OpenEAR
- Xilinx
- Auditory Toolbox
- rastamat
- BSS Eval
- Soft-LOST
- Kaldi
- LibriSpeech
- iNNvestigate
- Clockwork RNN
- Evolino
- RxR
- Speech bandwidth extension aided by magnitude spectrum data hiding
- Discrete sparse coding
- Understanding emergent dynamics: using a collective activity coordinate of a neural network to recognize time-varying patterns
- A novel fuzzy clustering algorithm using observation weighting and context information for reverberant blind speech separation
- Kernel approximation methods for speech recognition
- Learning midlevel auditory codes from natural sound statistics
- Active learning for logistic regression: an evaluation
- Information-theoretic regularization for learning global features by sequential VAE
- Constrained-storage multistage vector quantization based on genetic algorithms
- Type-2 fuzzy Gaussian mixture models
- Recurrent kernel machines: computing with infinite echo state networks
- Visually Grounded Models of Spoken Language: A Survey of Datasets, Architectures and Evaluation Techniques
This page was built for software: DARPA TIMIT
