Preprint
PiDA: Phonetically-Informed Data Augmentation for Robust Vietnamese Speech Translation
Giang Son Nguyen et al., arXiv, 2026
Read the originalRead on October 17, 2026
- What it is
- A June 2026 preprint, accepted to INTERSPEECH 2026, that measures how speech recognition errors in Vietnamese lower the quality of English translations. It uses the Vietnamese to English subset of the FLEURS benchmark.
- How much weight it carries
- A recent preprint accepted to a major speech conference, read on 2026-10-17. It covers one language pair, Vietnamese to English, so its BLEU drops should not be read as a figure for other languages.
Facts taken from this source
- A 2026 study found that on the Vietnamese to English subset of FLEURS, translating recognizer output instead of clean transcripts cost between 6.79 and 10.64 BLEU.
“6.79 to 10.64 BLEU drops when translating ASR outputs instead of clean transcripts” (Introduction)
- The 2026 Vietnamese study found that most recognition substitution errors come from sound-alike confusions, and that these errors significantly degrade translation quality.
“and that these phonetic errors significantly degrade ST quality” (Abstract)
Pages that rest on this source
- Speech to Text With Translation on Phones and ComputersGuide
- How accurate is speech to text translation?Question
- How do you translate a voice note to text?Question
- How do you translate an audio file into another language?Question
- How do you voice type in Hindi and get English text?Question
- How do you voice type in Urdu?Question