Semi- and self-supervised training techniques have the potential to improve performance of speech recognition systems without additional transcribed speech�...
Semi and self-supervised training techniques have the potential to improve performance of speech recognition systems without additional transcribed speech data.
Thus, many semi-supervised learning algorithms have been proposed to efficiently train ASR models with the help of untranscribed speech [4][5][6] [7] [8][9][10�...
We use multilingual pre-training with random-projection quantization and speech-text modality matching to achieve state-of-the-art performance on downstream�...
In this work, we demonstrate the efficacy of two approaches to semi-supervision for automated speech recognition. The two approaches leverage vast amounts of�...
Semi-Supervision in ASR: Sequential MixMatch and Factorized TTS-Based Augmentation � Zhehuai ChenA. Rosenberg +7 authors. P. Moreno. Computer Science.
Semi-Supervision in ASR: Sequential Mixmatch and Factorized TTS-Based Augmentation. Zhehuai Chen. Andrew Rosenberg. Yu Zhang. Heiga Zen (Byungha Chun).
Co-authors ; Semi-Supervision in ASR: Sequential MixMatch and Factorized TTS-Based Augmentation. Z Chen, A Rosenberg, Y Zhang, H Zen, M Ghodsi, Y Huang, J Emond,�...
Abstract—We summarize the results of a host of efforts using giant automatic speech recognition (ASR) models pre-trained using large, diverse unlabeled datasets�...
Semi-Supervision in ASR: Sequential Mixmatch and Factorized TTS-Based Augmentation. Zhehuai Chen. Andrew Rosenberg. Yu Zhang. Heiga Zen (Byungha Chun).