Back to results
US 9,959,864 B1Granted
Location-based voice query recognition
AssigneeGoogle Inc.
InventorCarl-Anton Ingmarsson
Life of this patent
Estimating the term…
Abstract
In some implementations, systems and methods are capable of performing location-based voice query recognition. Audio corresponding to an utterance of the user and data indicating a location associated with a user are initially received. An initial transcription of the utterance is then obtained. A set of n-grams that are associated with a region are selected for each of multiple regions that are associated with the location. One or more additional candidate descriptions are generated for one or more of the multiple geographic regions. A representative transcription of the utterance is selected for one or more of the multiple geographic regions. The representative transcription is finally provided to an automated speech recognizer.
Claims18
A computer-implemented method comprising:
- receiving, by a voice query processing system that includes (a) an automated speech recognizer (ASR), (b) a candidate transcription expander, and (c) a search engine, (i) audio data corresponding to an utterance of the user, and (ii) data indicating a location associated with a user;
- obtaining, based on processing the audio data by ASR of the voice query processing system, an initial candidate transcription of the utterance;
- selecting, by the candidate transcription expander of the voice query processing system and for each of multiple geographic regions that are associated with the location, a set of n-grams that represent names of entities that are pre-associated with the geographic region;
- for one or more of the multiple geographic regions, generating, by the candidate transcription expander of the voice query processing system and based on the set of n-grams that represent names of entities that are pre-associated with the geographic region, one more additional candidate transcriptions that are indicated as phonetically similar to one or more terms that do occur in the initial candidate transcription that is obtained by the ASR and that do not occur in the initial candidate transcription that is obtained by the ASR;
- selecting, by the ASR of the voice query processing system, from among the one or more additional candidate transcriptions that were generated by the candidate transcription expander and that are indicated as phonetically similar to one or more terms that do occur in the initial candidate transcription that is obtained by the ASR and that do not occur in the initial candidate transcription that is obtained by the ASR, a representative transcription of the utterance based on a phonetic similarity of the candidate transcriptions to the audio data;
- providing, by the voice query processing system, the representative transcription that was generated by the candidate transcription expander and that is indicated as phonetically similar to one or more terms that do occur in the initial candidate transcription that is obtained by the ASR and that does not occur in the initial candidate transcription that is obtained by the ASR for output as a likely most accurate transcription generated by the ASR;
- and
- processing the representative transcription as a query by the search engine to generate one or more search engine results.
5 more elements
A voice query processing system including (a) an automated speech recognizer (ASR), (b) a candidate transcription expander, and (c) a search engine, the voice query processing system comprising:
- one or more computers;
- and
- one or more data storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising:
- receiving (i) audio data corresponding to an utterance of the user, and (ii) data indicating a location associated with a user;
- obtaining, based on processing the audio data by the ASR of the voice query processing system, an initial candidate transcription of the utterance;
- selecting, by the candidate transcription expander of the voice query processing system and for each of multiple geographic regions that are associated with the location, a set of n-grams that represent names of entities that are pre-associated with the geographic region;
- for one or more of the multiple geographic regions, generating, by the candidate transcription expander of the voice query processing system and based on the set of n-grams that represent names of entities that are pre-associated with the geographic region, one more additional candidate transcriptions that are indicated as phonetically similar to one or more terms that do occur in the initial candidate transcription that is obtained by the ASR and that do not occur in the initial candidate transcription that is obtained by the ASR;
- selecting, by the ASR of the voice query processing system, from among the one or more additional candidate transcriptions that were generated by the candidate transcription expander and that are indicated as phonetically similar to one or more terms that do occur in the initial candidate transcription that is obtained by the ASR and that do not occur in the initial candidate transcription that is obtained by the ASR, a representative transcription of the utterance based on a phonetic similarity of the candidate transcriptions to the audio data;
- providing, by the voice query processing system, the representative transcription that was generated by the candidate transcription expander and that is indicated as phonetically similar to one or more terms that do occur in the initial candidate transcription that is obtained by the ASR and that does not occur in the initial candidate transcription that is obtained by the ASR for output as a likely most accurate transcription generated by the ASR;
- and
- processing the representative transcription as a query by the search engine to generate one or more search engine results.
8 more elements
A non-transitory computer-readable medium storing software comprising instructions executable by one or more computers which, upon such execution, cause the one or more computers to perform operations comprising:
- receiving, by a voice query processing system that includes (a) an automated speech recognizer (ASR), (b) a candidate transcription expander, and (c) a search engine, (i) audio data corresponding to an utterance of the user, and (ii) data indicating a location associated with a user;
- obtaining, based on processing the audio data by ASR of the voice query processing system, an initial candidate transcription of the utterance;
- selecting, by the candidate transcription expander of the voice query processing system and for each of multiple geographic regions that are associated with the location, a set of n-grams that represent names of entities that are pre-associated with the geographic region;
- for one or more of the multiple geographic regions, generating, by the candidate transcription expander of the voice query processing system and based on the set of n-grams that represent names of entities that are pre-associated with the geographic region, one more additional candidate transcriptions that are indicated as phonetically similar to one or more terms that do occur in the initial candidate transcription that is obtained by the ASR and that do not occur in the initial candidate transcription that is obtained by the ASR;
- selecting, by the ASR of the voice query processing system, from among the one or more additional candidate transcriptions that were generated by the candidate transcription expander and that are indicated as phonetically similar to one or more terms that do occur in the initial candidate transcription that is obtained by the ASR and that do not occur in the initial candidate transcription that is obtained by the ASR, a representative transcription of the utterance based on a phonetic similarity of the candidate transcriptions to the audio data;
- providing, by the voice query processing system, the representative transcription that was generated by the candidate transcription expander and that is indicated as phonetically similar to one or more terms that do occur in the initial candidate transcription that is obtained by the ASR and that does not occur in the initial candidate transcription that is obtained by the ASR for output as a likely most accurate transcription generated by the ASR;
- and
- processing the representative transcription as a query by the search engine to generate one or more search engine results.
5 more elements
Dependencies are inferred from the claim text.