Dialectal Speech Recognition and Translation of Swiss German Speech to Standard German Text: Microsoft's Submission to SwissText 2021

TL;DR

This paper presents Microsoft's winning approach for Swiss German speech recognition and translation, combining hybrid models, transfer learning, and neural language models to effectively convert Swiss German dialects into standard German text, achieving high BLEU scores.

Contribution

The paper introduces a hybrid ASR system with translation-aware lexicon, transfer-learned acoustic models, and neural language models tailored for Swiss German dialects, advancing dialect recognition and translation.

Findings

Achieved 46.04% BLEU score on blind test set

Outperformed second place by 12% relative margin

Effective handling of Swiss German dialectal features

Abstract

This paper describes the winning approach in the Shared Task 3 at SwissText 2021 on Swiss German Speech to Standard German Text, a public competition on dialect recognition and translation. Swiss German refers to the multitude of Alemannic dialects spoken in the German-speaking parts of Switzerland. Swiss German differs significantly from standard German in pronunciation, word inventory and grammar. It is mostly incomprehensible to native German speakers. Moreover, it lacks a standardized written script. To solve the challenging task, we propose a hybrid automatic speech recognition system with a lexicon that incorporates translations, a 1st pass language model that deals with Swiss German particularities, a transfer-learned acoustic model and a strong neural language model for 2nd pass rescoring. Our submission reaches 46.04% BLEU on a blind conversational test set and outperforms the second best competitor by a 12% relative margin.