Recently, the speech community is seeing a significant trend of moving from deep neural
network based hybrid modeling to end-to-end (E2E) modeling for automatic speech …

In the last decade of automatic speech recognition (ASR) research, the introduction of deep
learning has brought considerable reductions in word error rate of more than 50% relative …

We present state-of-the-art automatic speech recognition (ASR) systems employing a
standard hybrid DNN/HMM architecture compared to an attention-based encoder-decoder …

Current state-of-the-art approaches to offline Handwritten Text Recognition extensively rely
on Multidimensional Long Short-Term Memory networks. However, these architectures …

Sequence-to-sequence attention-based models on subword units allow simple open-
vocabulary end-to-end speech recognition. In this work, we show that such models can …

Multidimensional long short-term memory recurrent neural networks achieve impressive
results for handwriting recognition. However, with current CPU-based implementations, their …

Recent experiments show that deep bidirectional long short-term memory (BLSTM) recurrent
neural network acoustic models outperform feedforward neural networks for automatic …

Recent advances in text-to-speech (TTS) led to the development of flexible multi-speaker
end-to-end TTS systems. We extend state-of-the-art attention-based automatic speech …

In this paper, we present a new on-device automatic speech recognition (ASR) system
based on monotonic chunk-wise attention (MoChA) models trained with large (> 10K hours) …

This work investigates a simple data augmentation technique, SpecAugment, for end-to-end
speech translation. SpecAugment is a low-cost implementation method applied directly to …