公开(公告)号：US11417322B2

公开(公告)日：2022-08-16

申请号：US16712492

申请日：2019-12-12

Applicant: Google LLC

Inventor： Bhuvana Ramabhadran ,  Min Ma ,  Pedro J. Moreno Mengibar ,  Jesse Emond ,  Brian E. Roark

IPC: G10L15/19 ,  G10L15/06 ,  G10L15/16 ,  G10L15/22 ,  G06N3/08 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs stored on a computer-readable storage medium, for transliteration for speech recognition training and scoring. In some implementations, language examples are accessed, some of which include words in a first script and words in one or more other scripts. At least portions of some of the language examples are transliterated to the first script to generate a training data set. A language model is generated based on occurrences of the different sequences of words in the training data set in the first script. The language model is used to perform speech recognition for an utterance.