Preprint
Code-switching Speech Recognition Under the Lens: Model- and Data-Centric Perspectives
Hexin Liu et al., arXiv, 2025
Read the originalRead on October 17, 2026
- What it is
- A September 2025 preprint that analyzes code-switching speech recognition, where a speaker mixes two languages within a sentence. It compares modeling methods and studies how synthetic speech and accent affect results.
- How much weight it carries
- A preprint, not confirmed as peer reviewed at the time of checking. Its experiments use public code-switching test sets, so its findings describe those sets and language pairs, not every mix of languages.
Facts taken from this source
- The authors say that spontaneous switching within a sentence causes language confusion for code-switching recognizers, and that accent bias blurs the sound boundaries between languages.
“language confusion introduced by spontaneous intra-sentence switching and accent bias that blurs the phonetic boundaries” (Abstract)
- The authors say that even when each language in a mix is well resourced, the shortage of annotated code-switched audio makes recognition harder.
“Although the constituent languages may be individually high-resource, the scarcity of annotated code-switching data further compounds these challenges.” (Abstract)
Pages that rest on this source
- Hindi Voice Typing and Speech to TextGuide
- Speech Recognition and Accents: Accuracy and FixesGuide
- Multilingual Dictation: Two Languages, Auto-Detect, MixingGuide
- Transcribe and Translate Audio in Other LanguagesGuide
- Can speech to text handle Hinglish, Spanglish and other mixed languages?Question
- Can you dictate in two languages at the same time?Question
- How do you transcribe Arabic or Hebrew audio to text?Question
- How do you transcribe Hindi or Hinglish audio to text?Question
- How do you transcribe Japanese, Chinese or Korean audio?Question
- How do you transcribe Tamil, Urdu, Bengali or other South Asian audio?Question
- How do you translate a voice recording into English text?Question
- Code-switchingGlossary
- How do you voice type in Urdu?Question
- Low-resource languageGlossary