End-to-End Training of Acoustic Models for Large Vocabulary Continuous Speech Recognition with TensorFlow
By Ehsan Variani, Tom Bagby, Erik McDermott, Michiel Bacchiani. 2017
28 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Speech & Audio
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
- Tara N. Sainath
- Jinyu Li
- Yoshua Bengio
- Bo Li
- Rohit Prabhavalkar
- Mirco Ravanelli
- Dong Yu
- Khe Chai Sim
In Speech & Audio
- Tara N. Sainath
- Jinyu Li
- Yoshua Bengio
- Mirco Ravanelli
- Khe Chai Sim
- Trevor Strohman
- Arun Narayanan
- David Rybach
Citations in the corpus
- Toward Domain-Invariant Speech Recognition via Large Scale Training (2018, background): “The trainer reads from the queue, and is not affected by the slowness of feature computation process as long as there are enough jobs feeding the queue [26].”
- A Density Ratio Approach to Language Model Fusion in End-to-End Automatic Speech Recognition (2019, background): “For much of the ASR community, this approach still constitutes the state-of-the-art [3, 22, 23].”
- Hybrid Autoregressive Transducer (HAT) (2020, methodology): “log Mel features extracted from a 64 ms window every 30 ms [28] .”
- SpeechBrain: A General-Purpose Speech Toolkit (2021, methodology): “A more sophisticated approach is to apply dynamic batching [68, 69], where sentences are clustered by length and sampled within the same cluster, a trade-off between random and sorted batching.”