Fully Neural Network Based Speech Recognition on Mobile and Embedded Devices
By Jinhwan Park, Yoonho Boo, Iksoo Choi, Sungho Shin, Wonyong Sung. 2018
50 citations recorded by the source corpus.
Subfields: Natural Language Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Natural Language Processing
- Gabriel Synnaeve
- Ronan Collobert
- Awni Y. Hannun
- Qiantong Xu
- Jacob Kahn
- Tatiana Likhomanenko
- Vineel Pratap
- Vitaliy Liptchinsky
Citations in the corpus
- End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures (2019, neutral): “For CTC decoding, following (Park et al., 2018), only the blank token is considered if its posterior probability is greater than 0.”
- Scaling Up Online Speech Recognition Using ConvNets (2020, methodology): “Second, we propose only the blank symbol if its posterior probability is larger than 0.95 [23].”
- Fully Quantized Transformer for Machine Translation (2019, background): “Lastly, Park et al. (2018) introduce simple recurrent units (SRUs) for easy pruning of RNNs.”