Towards Language-Universal End-to-End Speech Recognition
This work addresses the need for efficient multilingual speech recognition, offering a novel method that reduces the complexity of training separate models for each language.
The paper tackled the problem of building multilingual speech recognition systems by proposing a single model with a universal character set and language-specific gating, which outperformed monolingual and multi-task learning approaches on the Microsoft Cortana task across three languages.
Building speech recognizers in multiple languages typically involves replicating a monolingual training recipe for each language, or utilizing a multi-task learning approach where models for different languages have separate output labels but share some internal parameters. In this work, we exploit recent progress in end-to-end speech recognition to create a single multilingual speech recognition system capable of recognizing any of the languages seen in training. To do so, we propose the use of a universal character set that is shared among all languages. We also create a language-specific gating mechanism within the network that can modulate the network's internal representations in a language-specific way. We evaluate our proposed approach on the Microsoft Cortana task across three languages and show that our system outperforms both the individual monolingual systems and systems built with a multi-task learning approach. We also show that this model can be used to initialize a monolingual speech recognizer, and can be used to create a bilingual model for use in code-switching scenarios.