Dual-Form ASR: Semantics-Aware Inverse Text Normalization for Chinese Speech Recognition

arXiv 2609.02901v1dfb0f960f502a59b82c5e0046d90d929db353fde4bd6dcb549ecf90b0642a61d

Paper metadata

arXiv ID
2609.02901
Version
v1
Category
cs.CL, cs.SD
Authors
Fengrun Zhang, Li Fu, Wangjin Zhou, Lu Fan, Youzheng Wu, Xiaodong He
Publication date
2026-09-04T04:00:00Z
Source identifier
2609.02901v1
Public record ID
record:sha256:dfb0f960f502a59b82c5e0046d90d929db353fde4bd6dcb549ecf90b0642a61d

Source license ↗

The PDF link points to arxiv.org. Baitaphish does not expose a private stored PDF.

This is source-provided metadata, not an enriched summary or an impact assessment. Follow the canonical source link for the published material.

Evidence and limitations

Source ID
arxiv_research
Record identifier
dfb0f960f502a59b82c5e0046d90d929db353fde4bd6dcb549ecf90b0642a61d
Record type
Source metadata

This record may overlap with other records. Source metadata can be incomplete or change. Validate consequential decisions against the linked source and your own environment.