A comprehensive analysis on attention models
By Albert Zeyer, Hermann Ney, Andr'e Merboldt, Ralf Schlüter. 2019
18 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Model Architectures
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
- Ralf Schlüter
- Hermann Ney
- Kazuki Irie
- Albert Zeyer
- Markus Kitza
- Wilfried Michel
- Parnia Bahar
- Eugen Beck
In Computer Vision and Pattern Recognition
- Hermann Ney
- Albert Zeyer
- Ralf Schlüter
- Kazuki Irie
- Parnia Bahar
- Wilfried Michel
- Markus Kitza
- Eugen Beck
In Model Architectures
Citations in the corpus
- RWTH ASR Systems for LibriSpeech: Hybrid vs Attention - w/o Data Augmentation (2019, methodology): “Compared to the system in [6] we use an extended pretraining variant where we not only grow the encoder depth but also grow the hidden dimension of the LSTMs.”
- SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition (2019, neutral): “, (2018) [38] 4.”
- End-to-End Speech Recognition: A Survey (2023, unknown): “Supervisedlayer-wisepretraininghas beensuccessfullyappliedforclassical[5],[145],aswellas attention-basedASRmodels[146],whichcanbecombinedwith intermediatesub-samplingschemes[147],andmodelgrow-ing[148].”
- A Comparison of Transformer and LSTM Encoder Decoder Models for ASR (2019, methodology): “The LibriSpeech ASR used here is based on [14, 48, 49].”