Automatic speech recognition using multiple language models
AssigneeZoom Communications, Inc.
InventorsThai Son Nguyen, Jie Pu, Sebastian Stüker
Life of this patent
Estimating the term…
Abstract
One example method includes receiving an audio stream comprising speech; generating, by automatic speech recognition (“ASR”) software, a plurality of hypotheses, each hypothesis comprising a transcription of a first portion of the speech; rescoring, using a first trained language model, each hypothesis of the plurality of hypotheses; and responsive to a first hypothesis not satisfying a threshold, generating and outputting, using a trained large language model (“LLM”), a final transcription based on the plurality of hypotheses.
Claims20
A method comprising:
- receiving an audio stream comprising speech;
- generating, by automatic speech recognition (“ASR”) software, a plurality of hypotheses, each hypothesis comprising a transcription of a first portion of the speech;
- rescoring, using a first trained language model, each hypothesis of the plurality of hypotheses;
- and
- responsive to a first hypothesis not satisfying a threshold, generating and outputting, using a trained large language model (“LLM”), a final transcription based on the plurality of hypotheses.
A system comprising:
- a communications interface;
- a non-transitory computer-readable medium;
- and
- one or more processors configured to execute processor-executable instructions stored in the non-transitory computer-readable medium to:
- receive an audio stream comprising speech;
- generate, by automatic speech recognition (“ASR”) software, a plurality of hypotheses, each hypothesis comprising a transcription of a first portion of the speech;
- rescore, using a first trained language model, each hypothesis of the plurality of hypotheses;
- and
- responsive to a first hypothesis not satisfying a threshold, generate and output, using a trained large language model (“LLM”), a final transcription based on the plurality of hypotheses.
A non-transitory computer-readable medium comprising processor-executable instructions configured to cause one or more processors to:
- receive an audio stream comprising speech;
- generate, by automatic speech recognition (“ASR”) software, a plurality of hypotheses, each hypothesis comprising a transcription of a first portion of the speech;
- rescore, using a first trained language model, each hypothesis of the plurality of hypotheses;
- and
- responsive to a first hypothesis not satisfying a threshold, generate and output, using a trained large language model (“LLM”), a final transcription based on the plurality of hypotheses.
Dependencies are inferred from the claim text.