Method and system for speech recognition
AssigneeAlibaba Group Holding Limited
InventorsShiliang ZHANG, Ming LEI
Life of this patent
Estimating the term…
Abstract
Embodiments of the disclosure provide a method and system for speech recognition. The method comprises dividing space into a plurality of regions based on preset DOA angles to allocate a signal source to the plurality of regions, wherein signals in the plurality of regions are enhanced and recognized, the result of which are fused to obtain a recognition result of the signal source.
Claims21
1-13. (canceled)
A method comprising:
- allocating a signal source based on different directions of arrival (DOAs);
- enhancing signals of the signal source corresponding to the different DOAs;
- performing speech recognition on the enhanced signals corresponding to the different DOAs to obtain recognition results corresponding to the different DOAs;
- providing the recognition results corresponding to the different DOAs to respective acoustic models;
- and
- fusing outputs of the acoustic models to obtain a recognition result.
A system comprising:
- a processor;
- and
- a storage medium for tangibly storing thereon program logic for execution by the processor, the stored program logic comprising:
- logic, executed by the processor, for allocating a signal source based on different directions of arrival (DOAs),
- logic, executed by the processor, for enhancing signals of the signal source corresponding to the different DOAs, respectively,
- logic, executed by the processor, for performing speech recognition on the enhanced signals corresponding to the different DOAs to obtain recognition results corresponding to the different DOAs,
- logic, executed by the processor, for providing the recognition results corresponding to the different DOAs to respective acoustic models, and
- logic, executed by the processor, for fusing output results from the acoustic models to obtain a recognition result.
A non-transitory computer-readable storage medium for tangibly storing computer program instructions capable of being executed by a computer processor, the computer program instructions defining:
- allocating a signal source based on different directions of arrival (DOAs);
- enhancing signals of the signal source corresponding to the different DOAs;
- performing speech recognition on the enhanced signals corresponding to the different DOAs to obtain recognition results corresponding to the different DOAs;
- providing the recognition results corresponding to the different DOAs to respective acoustic models;
- and
- fusing output results from the acoustic models to obtain a recognition result.
Dependencies are inferred from the claim text.