Preprint
Combined Acoustic and Pronunciation Modelling for Non-Native Speech Recognition
Ghazi Bouselmi et al., arXiv, 2007
Read the originalRead on October 16, 2026
- What it is
- A 2007 paper from INRIA Lorraine that tests pronunciation modelling and acoustic adaptation methods for non-native speech recognition, using the HIWIRE database of foreign-accented English.
- How much weight it carries
- Preprint from 2007, using recognizers of that period and a research database. The reduction shows what adaptation can achieve on accented speech, not what a current dictation app will achieve.
Facts taken from this source
- In a 2007 study of foreign-accented English, the best combination of pronunciation modelling and acoustic adaptation cut word error rate by 46 to 71 percent relative.
“The best combination of the above mentioned techniques resulted in a relative word error reduction ranging from 46% to 71%.” (Abstract)
Pages that rest on this source
- Dictation Languages: What Each App and Device SupportsGuide
- How Speech Recognition Works, From Sound to TextGuide
- Speech Recognition and Accents: Accuracy and FixesGuide
- Dictation for Language Learning: How and Why It WorksGuide
- Can dictation help non-native English speakers write work emails?Question
- Can you train dictation software to your accent?Question
- Can you use voice typing to practice pronunciation?Question
- How do you dictate foreign names and words correctly?Question
- Is speech recognition less accurate in languages other than English?Question
- Acoustic modelGlossary
- Non-native speechGlossary