Jocelyn Huang

TL;DR: A new end-to-end neural acoustic model for automatic speech recognition that achieves near state-of-the-art accuracy on LibriSpeech and Wall Street Journal, while having fewer parameters than all competing models.

TL;DR: NeMo (Neural Modules) is a Python framework-agnostic toolkit for creating AI applications through re-usability, abstraction, and composition that provides built-in support for distributed training and mixed precision on latest NVIDIA GPUs.

TL;DR: In this paper, an end-to-end neural acoustic model for automatic speech recognition is proposed, which is composed of multiple blocks with residual connections between them, each block consists of one or more modules with 1D time-channel separable convolutional layers.

TL;DR: This paper demonstrates the efficacy of transfer learning and continuous learning for various automatic speech recognition (ASR) tasks and shows that in all three cases, transfer learning from a good base model has higher accuracy than a model trained from scratch.

TL;DR: This paper demonstrates the efficacy of transfer learning and continuous learning for various automatic speech recognition (ASR) tasks using end-to-end models trained with CTC loss, and indicates that, for fine-tuning, larger pre-trained models are better than small pre- trained models, even if the dataset for Finetuning is small.