Patent · US Active

Lookup-table recurrent language model

US12412566B2 · kind B2 · utility

0Cited by
4References
22Claims
0Family size

Assignee

Inventors

Key dates

Filing dateFeb 10, 2022
Grant dateSep 9, 2025
Priority date
Expiry dateAug 7, 2043

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG10L2015/088
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A computer-implemented method includes receiving audio data that corresponds to an utterance spoken by a user and captured by a user device. The method also includes processing the audio data to determine a candidate transcription that includes a sequence of tokens for the spoken utterance. Tor each token in the sequence of tokens, the method includes determining a token embedding for corresponding token, determining a n-gram token embedding for a previous sequence of n-gram tokens, and concatenating the token embedding and the n-gram token embedding to generate a concatenated output for the corresponding token. The method also includes rescoring the candidate transcription for the spoken utterance by processing the concatenated output generated for each corresponding token in the sequence of tokens.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.