Similar Items: A low parameter channel grouped iterative convolutional recurrent network for speech enhancement of noise-reducing headphones
- Speech recognition in adverse conditions: synthetic transformations and real environmental noise
- A unified deep learning framework for estimating acoustic context parameters from first order ambisonic speech recordings
- Can speed perturbation plus SpecAugment be outperformed by novel combinations of speech data augmentations for ASR? A low-resource evaluation
- Detection of actionable domain shifts in speech enhancement systems by tracking prediction uncertainty
- Learning-based a posteriori speech presence probability estimation and applications
- Leveraging broadcast media subtitle transcripts for automatic speech recognition and subtitling