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

Researchers propose Dual-Form ASR (DF-ASR), a framework that extends spoken-form automatic speech recognition to semantics-aware written-form inverse text normalization for Chinese, using paired supervision and a sequence-level objective. On manually annotated Chinese subsets from SpeechIO, DF-ASR outperforms open-source ASR-ITN systems and remains competitive with closed-source references.

arXiv:2609.02901v1 Announce Type: new Abstract: Modern automatic speech recognition ASR scenarios require both spoken-form transcripts for faithful transcription and readable written-form transcripts with inverse text normalization ITN . However, these forms are typically produced by cascaded modules, where a spoken-form ASR output is rewritten by a separate ITN component, making written-form ASR-ITN vulnerable to recognition errors and decoupling normalization from acoustic-contextual modeling, especially for semantically dependent numeric expressions. In this paper, we propose Dual-Form ASR DF-ASR , a framework that extends spoken-form ASR capability to semantics-aware written-form ITN through paired spoken-form and written-form supervision while retaining prompt-level selection between transcript forms. The dual-form supervision is constructed via a large language model LLM -driven generate-and-judge workflow, and training is further enhanced by ITN-MWER, a sequence-level objective that assigns higher cost to errors on normalization-sensitive spans. We also introduce a decision-aware REQUIRE-ITN/\FORBID-ITN protocol to separately measure required normalization and forbidden-span preservation. On manually annotated Chinese subsets from SpeechIO, DF-ASR consistently outperforms open-source ASR-ITN systems, remains competitive with strong closed-source references, and preserves reliable prompt-level control between spoken-form and written-form outputs.