Recently, several types of end-to-end speech recognition methods named
transformer-transducer were introduced. According to those kinds of methods,
transcription networks are generally modeled by transformer-based neural
networks, while prediction networks could be modeled by either transformers or
recurrent neural networks (RNN). This paper explores multitask learning, joint
optimization, and joint decoding methods for transformer-RNN-transducer
systems. Our proposed methods have the main advantage in that the model can
maintain information on the large text corpus. We prove their effectiveness by
performing experiments utilizing the well-known ESPNET toolkit for the widely
used Librispeech datasets. We also show that the proposed methods can reduce
word error rate (WER) by 16.6 % and 13.3 % for test-clean and test-other
datasets, respectively, without changing the overall model structure nor
exploiting an external LM.

本论文探讨了 transformer-RNN-transducer 系统的多任务学习、联合优化和联合解码方法，证明了这些方法能够有效地降低字词错误率，从而保持大型文本语料库的信息。