Training a device specific acoustic model
AssigneeSoundHound AI IP, LLC
InventorsKeyvan MOHAJER, Mehul PATEL
Life of this patent
Estimating the term…
Abstract
Custom acoustic models can be configured by developers by providing audio files with custom recordings. The custom acoustic model is trained by tuning a baseline model using the audio files. Audio files may contain custom noise to apply to clean speech for training. The custom acoustic model is provided as an alternative to a standard acoustic model. A speech recognition system can select an acoustic model for use upon receiving metadata about the device conditions or type. Speech recognition is performed on speech audio using one or more acoustic models. The result can be provided to developers through the user interface, and an error rate can be computed and also provided.
Claims20
A method of performing speech recognition comprising:
- storing a plurality of acoustic models associated with a device;
- preselecting, based on metadata, one or more trained acoustic models of the plurality of acoustic models;
- selecting, based on information included in the metadata, a trained acoustic model from the preselected one or more trained acoustic models, the selected trained acoustic model being trained with environmental features;
- and
- employing the selected trained acoustic model to recognize speech from natural language utterances.
A non-transitory computer readable medium storing code that, when executed by one or more processors, causes the one or more processors to perform operations including:
- storing a plurality of acoustic models associated with a device;
- preselecting, based on metadata, one or more trained acoustic models of the plurality of acoustic models;
- selecting, based on information included in the metadata, a trained acoustic model from the preselected one or more trained acoustic models, the selected trained acoustic model being trained with environmental features;
- and
- employing the selected trained acoustic model to recognize speech from natural language utterances.
A method of using a platform for configuring device-specific speech recognition, the method comprising:
- receiving a selection of a set of at least two acoustic models, the selection of the set of at least two acoustic models being received by an interaction with a user interface provided by a computer system;
- and
- providing received speech audio and metadata to a speech recognition system associated with the platform.
A non-transitory computer readable medium storing code that, when executed by one or more processors, causes the one or more processors to perform operations including:
- storing a plurality of acoustic models associated with a device;
- preselecting, based on metadata, one or more trained acoustic models of the plurality of acoustic models;
- selecting, based on information included in the metadata, a trained acoustic model from the preselected one or more trained acoustic models, the selected trained acoustic model being trained with environmental features;
- and
- employing the selected trained acoustic model to recognize speech from natural language utterances.
Dependencies are inferred from the claim text.