# RETURNN: The RWTH Extensible Training framework for Universal Recurrent Neural Networks

arXiv: https://arxiv.org/abs/1608.00895 · HTML: https://mlsanity.com/paper/1608.00895/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Aug 2016.

## Built on by (most cited first, 16 of 16)

- [Recent Advances in End-to-End Automatic Speech Recognition](https://mlsanity.com/paper/2111.01690/) (2021)
- [End-to-End Speech Recognition: A Survey](https://mlsanity.com/paper/2303.03329/) (2023)
- [Differentiable Allophone Graphs for Language-Universal Speech Recognition](https://mlsanity.com/paper/2107.11628/) (2021)
- [Comparing the Benefit of Synthetic Training Data for Various Automatic Speech Recognition Architectures](https://mlsanity.com/paper/2104.05379/) (2021)
- [MultiMed: Multilingual Medical Speech Recognition via Attention Encoder Decoder](https://mlsanity.com/paper/2409.14074/) (2024)
- [Equivalence of Segmental and Neural Transducer Modeling: A Proof of Concept](https://mlsanity.com/paper/2104.06104/) (2021)
- [Efficient Utilization of Large Pre-Trained Models for Low Resource ASR](https://mlsanity.com/paper/2210.15445/) (2022)
- [On the Relevance of Phoneme Duration Variability of Synthesized Training Data for Automatic Speech Recognition](https://mlsanity.com/paper/2310.08132/) (2023)
- [AppTek's Submission to the IWSLT 2022 Isometric Spoken Language Translation Task](https://mlsanity.com/paper/2205.05807/) (2022)
- [Development of Hybrid ASR Systems for Low Resource Medical Domain Conversational Telephone Speech](https://mlsanity.com/paper/2210.13397/) (2022)
- [Unsupervised Pre-Training for Vietnamese Automatic Speech Recognition in the HYKIST Project](https://mlsanity.com/paper/2309.15869/) (2023)
- [End-to-End Training of a Neural HMM with Label and Transition Probabilities](https://mlsanity.com/paper/2310.02724/) (2023)
- [Running Conventional Automatic Speech Recognition on Memristor Hardware: A Simulated Approach](https://mlsanity.com/paper/2505.24721/) (2025)
- [Automatic Learning of Subword Dependent Model Scales](https://mlsanity.com/paper/2110.09324/) (2021)
- [Analyzing the Importance of Blank for CTC-Based Knowledge Distillation](https://mlsanity.com/paper/2506.01503/) (2025)
- [Positional Encoding in the Context of Memristor-Based Analog Computation for Automatic Speech Recognition](https://mlsanity.com/paper/2606.13379/) (2026)

## Abstract (arXiv)

In this work we release our extensible and easily configurable neural network training software. It provides a rich set of functional layers with a particular focus on efficient training of recurrent neural network topologies on multiple GPUs. The source of the software package is public and freely available for academic research purposes and can be used as a framework or as a standalone tool which supports a flexible configuration. The software allows to train state-of-the-art deep bidirectional long short-term memory (LSTM) models on both one dimensional data like speech or two dimensional data like handwritten text and was used to develop successful submission systems in several evaluation campaigns.