On Online Attention-Based Speech Recognition and Joint Mandarin Character-Pinyin Training

By William Chan, Ian Lane. 2016

58 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Jinyu Li
2. Shinji Watanabe
3. Yu Zhang
4. Takaaki Hori
5. Tara N. Sainath
6. Dong Yu
7. Yonghui Wu
8. Bo Xu

In Signal Processing

1. Jinyu Li
2. Shinji Watanabe
3. Takaaki Hori
4. Yu Zhang
5. Tara N. Sainath
6. Dong Yu
7. Bo Xu
8. Yonghui Wu

Citations in the corpus

• A Comparison of Modeling Units in Sequence-to-Sequence Speech Recognition with the Transformer on Mandarin Chinese (2018, background): “Character-based sequence-to-sequence attentionbased models have been investigated on Mandarin Chinese ASR tasks in [7, 8], but the performance comparison with different modeling units are not explored before.”
• Syllable-Based Sequence-to-Sequence Speech Recognition with the Transformer in Mandarin Chinese (2018, background): “lated work Sequence-to-sequence attention-based models have shown very encouraging results on English ASR tasks [1, 8, 10]. However, it is quite difficult to apply it to Mandarin Chinese ASR tasks. In [11], Chan et al. proposed Character-Pinyin sequencearXiv:1804.10752v2 [eess.AS] 4 Jun 2018 to-seque”
• Very deep convolutional networks for end-to-end speech recognition (2016, methodology): “Recently, very deep CNNs architectures [15] have also been shown to be successful in ASR [16, 17], using more non-linearities, but fewer parameters.”
• Bytes Are All You Need: End-to-end Multilingual Speech Recognition and Synthesis with Bytes (2018, methodology): “For example, [8] built a Connectionist Temporal Classification (CTC) model to directly output graphemes, while [9–11] used graphemes in sequence-to-sequence (seq2seq) models.”
• Joint CTC-attention based end-to-end speech recognition using multi-task learning (2016, background): “End-to-end speech recognition is a recently proposed approach that directly transcribes speech to text without requiring predefined alignment between acoustic frames and characters [1, 2, 3, 4, 5, 6, 7, 8, 9].”
• Towards Online End-to-end Transformer Automatic Speech Recognition (2019, methodology): “For RNN models, the median or maximum of the attention distribution is used as a cue for shifting a fixed-length chunk, where the parameters of the original batch models are reused [5, 25, 26].”
• Advances in Joint CTC-Attention Based End-to-End Speech Recognition with a Deep CNN Encoder and RNN-LM (2017, methodology): “There are two major types of end-to-end architectures for ASR: attention-based methods use an attention mechanism to perform alignment between acoustic frames and recognized symbols [5, 6, 7, 8, 9], and Connectionist Temporal Classification (CTC), uses Markov assumptions to efficiently solve sequent”
• Comparable Study Of Modeling Units For End-To-End Mandarin Speech Recognition (2018, methodology): “The other is attention-based encoder-decoder model [9, 10, 11, 12] which applies an attention mechanism to perform alignment between acoustic frames and recognized symbols.”
• Improving the Robustness of Speech Translation (2018, background): “The basic LAS model consists of three sub-modules: the listener, the attender and the speller.”