Delivering personalized user experiences with speaker adapted end-to-end...
… Delivering personalized user experiences with speaker adapted end-to-end speech recognition Read More » The post Delivering personalized user experiences with speaker adapted end-to-end speech...
View ArticleMaking speech recognizers more robust in the wild
… Making speech recognizers more robust in the wild Read More » The post Making speech recognizers more robust in the wild appeared first on What’s Next blog.
View ArticleDelivering non-intrusive signal intelligence with deep learning
… Delivering non-intrusive signal intelligence with deep learning Read More » The post Delivering non-intrusive signal intelligence with deep learning appeared first on What’s Next blog.
View ArticleCombining the advantages of close-talk and far-talk speech recognition
… Combining the advantages of close-talk and far-talk speech recognition Read More » The post Combining the advantages of close-talk and far-talk speech recognition appeared first on What’s Next blog.
View ArticleData augmentation for real-world multi-channel speech recognition
… Data augmentation for real-world multi-channel speech recognition Read More » The post Data augmentation for real-world multi-channel speech recognition appeared first on What’s Next blog.
View ArticlePrediction Network Architecture in RNN-T for ASR
… Prediction Network Architecture in RNN-T for ASR Read More » The post Prediction Network Architecture in RNN-T for ASR appeared first on What’s Next blog.
View Article