Automatic language identification for speech
First Claim
Patent Images
1. A method, comprising:
- determining, using GPS data and without receiving user input selecting a language model, a geographic location of an information handling device;
accessing, based upon the user'"'"'s geographic location, at least one language model corresponding to a predominant language associated with the geographic location of the information handling device;
receiving, at the information handling device, a user voice input containing a multitude of voice inputs in different languages, wherein each of the multitude of voice inputs is provided to the information handling device in a unique language and wherein the unique language is different from the predominant language;
identifying, by accessing a database of stored language models, the unique language associated with a wakeup word in each of the multitude of voice inputs; and
providing, subsequent to the identifying, an output response to each of the multitude of voice inputs in the predominant language.
2 Assignments
0 Petitions
Accused Products
Abstract
One embodiment provides a method, including: receiving, at an information handling device, voice input from at least one user; accessing at least one language model; determining, based upon the accessed at least one language model, at least one language of the voice input; and providing output associated with the voice input, based upon the determined language. Other aspects are described and claimed.
20 Citations
20 Claims
-
1. A method, comprising:
-
determining, using GPS data and without receiving user input selecting a language model, a geographic location of an information handling device; accessing, based upon the user'"'"'s geographic location, at least one language model corresponding to a predominant language associated with the geographic location of the information handling device; receiving, at the information handling device, a user voice input containing a multitude of voice inputs in different languages, wherein each of the multitude of voice inputs is provided to the information handling device in a unique language and wherein the unique language is different from the predominant language; identifying, by accessing a database of stored language models, the unique language associated with a wakeup word in each of the multitude of voice inputs; and providing, subsequent to the identifying, an output response to each of the multitude of voice inputs in the predominant language. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10)
-
-
11. An information handling device, comprising:
-
a processor; a memory device that stores instructions executable by the processor to; determine, using GPS data and without receiving user input selecting a language model, a geographic location of the information handling device; access, based upon the user'"'"'s geographic location, at least one language model corresponding to a predominant language associated with the geographic location of the information handling device; receive a user voice input containing a multitude of voice inputs in different languages, wherein each of the multitude of voice inputs is provided to the information handling device in a unique language and wherein the unique language is different from the predominant language; identify, by accessing a database of stored language models, the unique language associated with a wakeup word in each of the multitude of voice inputs; and provide, subsequent to the identifying, an output response to each of the multitude of voice inputs in the predominant language. - View Dependent Claims (12, 13, 14, 15, 16, 17, 18, 19)
-
-
20. A product, comprising:
-
a storage device that stores code, the code being executable by a processor and comprising; code that determines, using GPS data and without receiving user input selecting a language model, a geographic location of an information handling device; code that access, based upon the user'"'"'s geographic location, at least one language model corresponding to a predominant language associated with the geographic location of the information handling device; code that receives a user voice input containing a multitude of voice inputs in different languages, wherein each of the multitude of voice inputs is provided to the information handling device in a unique language and wherein the unique language is different from the predominant language; code that identifies, by accessing a database of stored language models, the unique language associated with a wakeup word in each of the multitude of voice inputs; and code that provides, subsequent to the identifying, an output response to each of the multitude of voice inputs in the predominant language.
-
Specification