Real-Time Statistical Speech Translation

TL;DR

This paper explores real-time statistical machine translation for speech, integrating speech recognition and synthesis, and evaluates various data preparation techniques and metrics for the PL-EN language pair.

Contribution

It presents a comprehensive approach to real-time speech translation using statistical models and evaluates multiple data processing methods and metrics.

Findings

Data preparation significantly affects translation quality.

BLEU, NIST, METEOR, and TER metrics vary in effectiveness.

Optimal data and metric choices improve real-time translation performance.

Abstract

This research investigates the Statistical Machine Translation approaches to translate speech in real time automatically. Such systems can be used in a pipeline with speech recognition and synthesis software in order to produce a real-time voice communication system between foreigners. We obtained three main data sets from spoken proceedings that represent three different types of human speech. TED, Europarl, and OPUS parallel text corpora were used as the basis for training of language models, for developmental tuning and testing of the translation system. We also conducted experiments involving part of speech tagging, compound splitting, linear language model interpolation, TrueCasing and morphosyntactic analysis. We evaluated the effects of variety of data preparations on the translation results using the BLEU, NIST, METEOR and TER metrics and tried to give answer which metric is most suitable for PL-EN language pair.