As more and more information-rich data like video become available, utilizing multi-modal auxiliary information to enhance audio tasks has sparked widespread research interest. The recent surge in research on LLM-based audio models provides fresh perspectives for tackling audio tasks. Given that LLM can flexibly ingest multiple inputs, we propose MaLa-ASR, an LLM-based ASR model that can integrate textual keywords extracted from presentation slides to improve recognition of conference content. MaLa-ASR yields average WERs of 9.4% and 11.7% on the L95 and S95 subsets of the SlideSpeech corpus, representing a significant relative WER drop of 27.9% and 44.7% over the baseline model reported in SlideSpeech. MaLa-ASR underscores LLM's strong performance in speech tasks and the capability to integrate auxiliary information conveniently. By adding keywords to the input prompt, the biased word error rate (B-WER) reduces relatively by 46.0% and 44.2%, establishing a new SOTA on this dataset.

提出了基于LLM的ASR模型MaLa-ASR，可以整合从演示文稿中提取的文本关键词来提高会议内容的识别率，通过在输入提示中添加关键词，可将有偏差的词错误率（B-WER）相对减少46.0％和44.2％，在该数据集上取得了新的SOTA。

MaLa-ASR: 多媒体辅助的基于LLM的ASR