Method and apparatus for recognizing voice
AssigneeBeijing Baidu Netcom Science Technology Co., Ltd.
InventorsXin LI, Bin HUANG, Ce ZHANG, Jinfeng BAI, Lei JIA
Life of this patent
Estimating the term…
Abstract
A method and an apparatus for recognizing a voice are provided. The method may include: inputting a target voice into a pre-trained voice recognition model to obtain an initial text output by at least one recognition network in the voice recognition model, the recognition network including a plurality of preset types of processing layers, and at least one type of processing layer of the recognition network being obtained by training based on a voice sample in a preset direction interval; and determining a voice recognition result of the target voice, based on the initial text.
Claims48
A method for recognizing a voice, the method comprising:
- inputting a target voice into a pre-trained voice recognition model to obtain an initial text output by at least one recognition network in the voice recognition model, the recognition network comprising a plurality of preset types of processing layers, and at least one type of processing layer of the recognition network being obtained by training based on a voice sample in a preset direction interval;
- and
- determining a voice recognition result of the target voice, based on the initial text.
A method for training a voice recognition model, the method comprising:
- acquiring a training sample, a voice sample for training in the training sample comprising a voice sample in a preset direction interval;
- inputting the voice sample for training into a to-be-trained voice recognition model to obtain an initial text output by at least one recognition network in the voice recognition model, the recognition network comprising a plurality of preset types of processing layers;
- and
- training the voice recognition model to obtain a trained voice recognition model, based on the initial text.
An electronic device, comprising:
- one or more processors;
- and
- a storage device, for storing one or more programs,
- wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
- inputting a target voice into a pre-trained voice recognition model to obtain an initial text output by at least one recognition network in the voice recognition model, the recognition network comprising a plurality of preset types of processing layers, and at least one type of processing layer of the recognition network being obtained by training based on a voice sample in a preset direction interval;
- and
- determining a voice recognition result of the target voice, based on the initial text.
An electronic device, comprising:
- one or more processors;
- and
- a storage device, for storing one or more programs,
- wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
- acquiring a training sample, a voice sample for training in the training sample comprising a voice sample in a preset direction interval;
- inputting the voice sample for training into a to-be-trained voice recognition model to obtain an initial text output by at least one recognition network in the voice recognition model, the recognition network comprising a plurality of preset types of processing layers;
- and
- training the voice recognition model to obtain a trained voice recognition model, based on the initial text.
Dependencies are inferred from the claim text.