Work

Data Augmentation for Pipeline-Based Speech Translation

Year: 2020

Type: book-chapter

Abstract: Pipeline-based speech translation methods may suffer from errors found in speech recognition system output. Therefore, it is crucial that machine translation systems are trained to be robust against such noise. In this paper, we propose two methods for parallel data augmentation for pipeline-based speech translation system development. The first method utilises a speech processing workflow to introduce errors and the second method generates commonly found suffix errors using a rule-based method. We show that the methods in combination allow significantly improving speech translation quality by 1.87 BLEU points over a baseline system.

Source: Frontiers in artificial intelligence and applications

DOI: 10.3233/faia200605

Authors: Diego Alves, Askars Salimbajevs, Mārcis Pinnis

Institutions: University of Zagreb, Faculty of Humanities and Social Sciences in Zagreb, Tilde (Latvia), University of Latvia

Language: English

Topic: Speech Recognition and Synthesis

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: European Commission

Awards: Cross-lingual Event-centric Open Analytics Research Academy, G434337789