Showing 1–20 of 46 results
/ Date/ Name
Jan 12, 2016Learning Hidden Unit Contributions for Unsupervised Acoustic Model AdaptationJul 1, 2019Synchronising audio and ultrasound by learning cross-modal embeddingsJun 27, 2019Lattice-Based Unsupervised Test-Time Adaptation of Neural Network Acoustic ModelsOct 4, 2019Cross lingual transfer learning for zero-resource domain adaptationMay 31, 2021Automatic audiovisual synchronisation for ultrasound tongue imagingOct 16, 2021Towards Robust Waveform-Based Acoustic ModelsMar 1, 2016Segmental Recurrent Neural Networks for End-to-end Speech RecognitionSep 21, 2017Speech Recognition Challenge in the Wild: Arabic MGB-3Mar 31, 2016Differentiable Pooling for Unsupervised Acoustic Model AdaptationJun 2, 2024Phonetic Error Analysis of Raw Waveform Acoustic Models with Parametric and Non-Parametric CNNsMay 28, 2020When Can Self-Attention Be Replaced by Feed Forward Layers?Oct 31, 2019Multi-scale Octave Convolutions for Robust Speech RecognitionJul 1, 2019Ultrasound tongue imaging for diarization and alignment of child speech therapy sessionsJul 1, 2019Speaker-independent classification of phonetic segments from raw ultrasound in child speechAug 8, 2020Word Error Rate Estimation Without ASR Output: e-WER2Nov 8, 2020Stochastic Attention Head Removal: A simple and effective method for improving Transformer Based ASR ModelsOct 27, 2020Leveraging speaker attribute information using multi task learning for speaker verification and diarizationFeb 27, 2021Silent versus modal multi-speaker speech recognition from ultrasound and videoAug 1, 2017End-to-End Neural Segmental Models for Speech RecognitionMar 30, 2000Information Extraction from Broadcast News