Enhancements in statistical spoken language translation by de-normalization of ASR results

TL;DR

This paper improves statistical spoken language translation by enhancing ASR output through de-normalization and automatic sentence segmentation, specifically focusing on Polish speech, to boost translation accuracy.

Contribution

It introduces a novel approach for automatic sentence segmentation and reverse normalization in Polish speech recognition, enhancing translation quality in SLT systems.

Findings

Improved sentence boundary detection in Polish ASR transcriptions.

Enhanced MT performance through de-normalization of ASR outputs.

Demonstrated effectiveness of proposed methods in experimental evaluations.

Abstract

Spoken language translation (SLT) has become very important in an increasingly globalized world. Machine translation (MT) for automatic speech recognition (ASR) systems is a major challenge of great interest. This research investigates that automatic sentence segmentation of speech that is important for enriching speech recognition output and for aiding downstream language processing. This article focuses on the automatic sentence segmentation of speech and improving MT results. We explore the problem of identifying sentence boundaries in the transcriptions produced by automatic speech recognition systems in the Polish language. We also experiment with reverse normalization of the recognized speech samples.