RASR/NN: The RWTH neural network toolkit for speech recognition

By Simon Wiesler, Alexander Richard, Pavel Golik, Ralf Schlüter, Hermann Ney. 2014

66 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Natural Language Processing, Speech & Audio, 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. Dong Yu
3. Ralf Schlüter
4. Li Deng
5. Hermann Ney
6. Albert Zeyer
7. Kazuki Irie
8. Jasha Droppo

In Natural Language Processing

1. Ralf Schlüter
2. Hermann Ney
3. Albert Zeyer
4. Dong Yu
5. Kazuki Irie
6. Li Deng
7. Kaisheng Yao
8. Jasha Droppo

In Speech & Audio

1. Ralf Schlüter
2. Hermann Ney
3. Dong Yu
4. Jinyu Li
5. Albert Zeyer
6. Kazuki Irie
7. Jasha Droppo
8. Geoffry Zweig

In Signal Processing

1. Dong Yu
2. Jinyu Li
3. Li Deng
4. M. Seltzer
5. Ralf Schlüter
6. Hermann Ney
7. Jasha Droppo
8. Frank Torsten Bernd Seide

Citations in the corpus

• RWTH ASR Systems for LibriSpeech: Hybrid vs Attention - w/o Data Augmentation (2019, methodology): “The decoding process was setup in RASR.”
• Improved training of end-to-end attention models for speech recognition (2018, methodology): “We use 40-dimensional Gam-matone features [58], and the feature extraction was done with RASR [59].”
• An introduction to computational networks and the computational network toolkit (invited talk) (2014, methodology): “This observation suggests that we can unify all these models under the framework of computational network (CN), part of which has been implemented in toolkits such as Theano [23], CNTK [24] and RASR/NN [25].”
• Returnn: The RWTH extensible training framework for universal recurrent neural networks (2016, methodology): “Task specific software packages like RASR [11] or Kaldi [21] which are both for developing speech recognition systems, contain modules to train and decode ASR systems, including neural networks.”
• A comprehensive analysis on attention models (2019, methodology): “In some cases, the feature extraction, and in the hybrid case the decoding, is performed with RASR [Wiesler et al., 2014].”
• A Comparative Study on End-to-End Speech to Text Translation (2019, methodology): “[32] Simon Wiesler, Alexander Richard, Pavel Golik, Ralf Schlüter, and Hermann Ney, “RASR/NN: the RWTH neural network toolkit for speech recognition,” in IEEE Inter.”
• The Rwth Asr System for Ted-Lium Release 2: Improving Hybrid Hmm With Specaugment (2020, methodology): “All trainings are done using our NN modeling toolkit RETURNN [15], our ASR toolkit RASR [16] and our work-flow manager Sisyphus [17].”
• A comprehensive study of deep bidirectional LSTM RNNS for acoustic modeling in speech recognition (2016, methodology): “Our base tool is the RASR speech recognition toolkit [21, 22].”