mlsanityData to 14 Oct 2026

RASR2: The RWTH ASR Toolkit for Generic Sequence-to-sequence Speech Recognition

arXiv 2305.17782 ↗First posted 28 May 2023cs.CL cs.SD eess.AScited by 3

Not on the map. Why?

Abstract (arXiv)

Modern public ASR tools usually provide rich support for training various sequence-to-sequence (S2S) models, but rather simple support for decoding open-vocabulary scenarios only. For closed-vocabulary scenarios, public tools supporting lexical-constrained decoding are usually only for classical ASR, or do not support all S2S models. To eliminate this restriction on research possibilities such as modeling unit choice, we present RASR2 in this work, a research-oriented generic S2S decoder implemented in C++. It offers a strong flexibility/compatibility for various S2S models, language models, label units/topologies and neural network architectures. It provides efficient decoding for both open- and closed-vocabulary scenarios based on a generalized search framework with rich support for different search modes and settings. We evaluate RASR2 with a wide range of experiments on both switchboard and Librispeech corpora. Our source code is public online.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 26 of its 44 references that are in the map. First posted on arXiv 28 May 2023.

Builds on

26 of 44 references.

References · 26

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,918
  3. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,863
  4. 2018ESPnet: End-to-End Speech Processing Toolkitcited by 558
  5. 2015Listen, Attend and Spellcited by 543
  6. 2021SpeechBrain: A General-Purpose Speech Toolkitcited by 406
  7. 2015End-to-End Attention-based Large Vocabulary Speech Recognitioncited by 151
  8. 2020Hybrid Autoregressive Transducer (hat)cited by 108
  9. 2019Language Modeling with Deep Transformerscited by 96
  10. 2018RETURNN as a Generic Flexible Neural Toolkit with Application to Translation and Speech Recognitioncited by 30
  11. 2019Sequence-to-Sequence Speech Recognition with Time-Depth Separable Convolutionscited by 27
  12. 2021Investigating Methods to Improve Language Model Integration for Attention-based Encoder-Decoder ASR Modelscited by 25
14 more
  1. 2022Flashlight: Enabling Innovation in Tools for Machine Learningcited by 25
  2. 2020Phoneme Based Neural Transducer for Large Vocabulary Speech Recognitioncited by 20
  3. 2021Fast Text-Only Domain Adaptation of RNN-Transducer Prediction Networkcited by 19
  4. 2021Internal Language Model Adaptation with Text-Only Data for End-to-End Speech Recognitioncited by 17
  5. 2021On Language Model Integration for RNN Transducer based Speech Recognitioncited by 17
  6. 2016Length bias in Encoder Decoder Models and a Case for Global Conditioningcited by 14
  7. 2022Efficient Training of Neural Transducer for Speech Recognitioncited by 14
  8. 2020An investigation of phone-based subword units for end-to-end speech recognitioncited by 12
  9. 2019LSTM Language Models for LVCSR in First-Pass Decoding and Lattice-Rescoringcited by 11
  10. 2021Acoustic Data-Driven Subword Modeling for End-to-End Speech Recognitioncited by 11
  11. 2021Equivalence of Segmental and Neural Transducer Modeling: A Proof of Conceptcited by 5
  12. 2020Robust Beam Search for Encoder-Decoder Attention Based Speech Recognition without Length Biascited by 4
  13. 2022HMM vs. CTC for Automatic Speech Recognition: Comparison Based on Full-Sum Training from Scratchcited by 4
  14. 2020Full-Sum Decoding for Hybrid HMM based Speech Recognition using LSTM Language Modelcited by 3

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 0; 2025: 1.

3 papers.

  1. 2025Regularizing Learnable Feature Extraction for Automatic Speech Recognitioncited by 2
  2. 2023On the Relation between Internal Language Model and Sequence Discriminative Training for Neural Transducerscited by 1
  3. 2023Investigating the Effect of Language Models in Sequence Discriminative Training for Neural Transducerscited by 0