Lost in Interpreting: Speech Translation from Source or Interpreter?
This work addresses the challenge of extending affordable language coverage in multi-lingual meetings, though it is incremental as it builds on existing speech translation methods.
The paper tackles the problem of whether automatic simultaneous speech translation should follow the original speaker or an interpreter to improve translation quality, finding that interpreter-based systems reduce latency but may increase information loss, with human evaluation showing up to 15% higher information retention for speaker-based approaches.
Interpreters facilitate multi-lingual meetings but the affordable set of languages is often smaller than what is needed. Automatic simultaneous speech translation can extend the set of provided languages. We investigate if such an automatic system should rather follow the original speaker, or an interpreter to achieve better translation quality at the cost of increased delay. To answer the question, we release Europarl Simultaneous Interpreting Corpus (ESIC), 10 hours of recordings and transcripts of European Parliament speeches in English, with simultaneous interpreting into Czech and German. We evaluate quality and latency of speaker-based and interpreter-based spoken translation systems from English to Czech. We study the differences in implicit simplification and summarization of the human interpreter compared to a machine translation system trained to shorten the output to some extent. Finally, we perform human evaluation to measure information loss of each of these approaches.