释放
发表于 2025-4-1 02:17:21
http://reply.papertrans.cn/88/8741/874037/874037_61.png
挫败
发表于 2025-4-1 09:06:47
A Decade of Discriminative Language Modeling for Automatic Speech Recognitione examples for DLM training come from the manual transcriptions of acoustic data while the negative examples are obtained by processing the same acoustic data with an ASR system. Recent research generalizes DLM training by either using automatic transcriptions for the positive examples or simulating