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

Interspeech (USB), pp. 4094–4098

Abstract

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.

Authors 5

1. Wei Guo Zhou Aachen Machine Learning and Human Language Technology Computer Science Department

   RWTH Aachen University

   Affiliation as printed

   AppTek GmbH, 52062 Aachen, Germany

   Machine Learning and Human Language Technology, Computer Science Department, RWTH Aachen University, 52074 Aachen, Germany

2. Eugen Beck
   Affiliation as printed

   AppTek GmbH, 52062 Aachen, Germany

3. Simon Berger Aachen Machine Learning and Human Language Technology Computer Science Department

   RWTH Aachen University

   Affiliation as printed

   AppTek GmbH, 52062 Aachen, Germany

   Machine Learning and Human Language Technology, Computer Science Department, RWTH Aachen University, 52074 Aachen, Germany

4. Ralf Schlüter Aachen Machine Learning and Human Language Technology Computer Science Department

   RWTH Aachen University

   Affiliation as printed

   AppTek GmbH, 52062 Aachen, Germany

   Machine Learning and Human Language Technology, Computer Science Department, RWTH Aachen University, 52074 Aachen, Germany

5. Hermann Ney Aachen Machine Learning and Human Language Technology Computer Science Department

   RWTH Aachen University

   Affiliation as printed

   AppTek GmbH, 52062 Aachen, Germany

   Machine Learning and Human Language Technology, Computer Science Department, RWTH Aachen University, 52074 Aachen, Germany