Peer-reviewed research
Syllable language models for Mandarin speech recognition: Exploiting character language models
Xunying Liu et al., Journal of the Acoustical Society of America, 2013
Read the originalRead on October 17, 2026
- What it is
- A speech recognition paper from Cambridge University and the International Computer Science Institute in Berkeley on language models for Mandarin Chinese, which is written with characters and no spaces between words. The paper explains why the character error rate, not the word error rate, is the usual metric for Mandarin systems.
- How much weight it carries
- Peer-reviewed journal article by an established speech group. It describes a 2010s broadcast-audio task, so the exact agreement figure reflects native-speaker tests of that period rather than current systems.
Facts taken from this source
- In tests of word boundary marking by native Mandarin speakers, their agreement on where the word boundaries fall was about 75 percent, so the authors use character error rate as the usual metric for Mandarin speech recognition.
“agreement on the boundary locations occurs approximately 75% of the time” (Introduction)
Pages that rest on this source
- Japanese, Chinese and Korean Speech to TextGuide
- Transcribe and Translate Audio in Other LanguagesGuide
- Do people speak faster in some languages?Question
- How do you transcribe Japanese, Chinese or Korean audio?Question
- Is speaking Chinese faster than typing pinyin?Question
- What is the difference between WER and character error rate?Question
- PinyinGlossary