INTEREST NOTIFICATION APPARATUS AND METHOD

• US 20170018272A1
• Filed: 07/14/2016
• Published: 01/19/2017
• Est. Priority Date: 07/16/2015
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: LEE, Ji Hyun, CHOI, Young Sang
• Granted Patent: US 10,521,514 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/685 using automatically derived transcript of audio data, e.g. lyrics speech recognition G10L15/00
• CPC Class Codes: G06F 16/90332 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 40/58 Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 25/51 for comparison or discrimination
• CPC Class Codes: H04N 21/4394 involving operations for analysing the audio stream, e.g. detecting features or characteristics in audio streams arrangements characterised by components specially adapted for monitoring, identification or recognition of audio in broadcast systems H04H60/58
• CPC Class Codes: H04N 21/4532 involving end-user characteristics, e.g. viewer profile, preferences monitoring of user activities for profile generation for accessing a video database G06F16/739; user profiles in network data switching protocols H04L67/306; processing of user preferences or user profiles in wireless networks H04W8/18
• CPC Class Codes: H04N 21/4668 for recommending content, e.g. movies
• CPC Class Codes: H04N 21/4755 for defining user preferences, e.g. favourite actors or genre retrieval personalisation and generation of user profiles for the retrieval of video data G06F16/739; user profiles in network data switching protocols H04L67/306

Abstract

An apparatus for notification of speech of interest to a user includes a voice analyzer configured to recognize speech, evaluate a relevance between a result of the speech recognition and a determined user'"'"'s topic of interest, and determine whether to provide a notification; and an outputter configured to, in response to the voice analyzer determining to provide the notification, generate and output a notification message.

Claims

1. A speech notification apparatus, the apparatus comprising:

a voice analyzer configured to recognize speech, evaluate a relevance between a result of the speech recognition and a determined user'"'"'s topic of interest, and determine whether to provide a notification; and

an outputter configured to, in response to the voice analyzer determining to provide the notification, generate and output a notification message.

2. The apparatus of claim 1, further comprising a topic-of-interest setter configured to determine a user'"'"'s topic of interest.

3. The apparatus of claim 2, wherein the topic-of-interest setter is further configured to determine the user'"'"'s topic of interest based on a user input or automatically determine the user'"'"'s topic of interest by analyzing user'"'"'s contextual information.

4. The apparatus of claim 3, wherein the contextual information comprises at least one of user'"'"'s schedule stored in the apparatus or location data determined by the apparatus.

5. The apparatus of claim 2, wherein, the topic-of-interest setter is further configured to learn the determined user'"'"'s topic of interest based on the evaluated relevance.

6. The apparatus of claim 2, wherein the voice analyzer comprises a text generator configured to generate text in the recognizing of the speech and a text analyzer configured to evaluate a relevance between the generated text and the user'"'"'s topic of interest.

7. The apparatus of claim 6, wherein the text analyzer is configured to apply at least one of support vector machine (SVM) classification or neural network classification to classify the generated text, and evaluate a relevance between a classification result and the user'"'"'s topic of interest in determining whether to provide the notification.

8. The apparatus of claim 6, wherein the text analyzer is further configured to evaluate the relevance between the text and the user'"'"'s topic of interest based on at least one of the following:

presence or absence of a user'"'"'s user keyword in the generated text, a number of user keywords in the text, or a number of words in the text relating to the user keyword, as respectively set by the topic-of-interest setter.

9. The apparatus of claim 2, wherein the outputter is further configured to output the notification message in at least one of the following forms:

text, a voice, a vibration, or an alerting sound.

10. The apparatus of claim 2, wherein the outputter is further configured to determine importance of notification based on the speech recognition result and select between plural notification methods according to the importance to output the notification.

11. The apparatus of claim 2, further comprising:

a voice translator configured to translate a language of the recognized speech into a language designated by the user for evaluation of the relevance in the designated language, or to translate the notification into the designated language after evaluation of the relevance in the language of the recognized speech.

12. A speech notification method, comprising:

actuating a processor portion to recognize speech, evaluating a relevance between a result of the speech recognition and a determined user'"'"'s topic of interest, and determining whether to provide a notification based on the evaluation; and

in response to the determination that the notification is provided to the user, generating and outputting, to the user, a notification message.

13. The method of claim 12, further comprising determining a user'"'"'s topic of interest.

14. The method of claim 13, wherein the determining of the user'"'"'s topic of interest comprises determining the user'"'"'s topic of interest based on a user input or automatically determining the user'"'"'s topic of interest by analyzing user'"'"'s contextual information.

15. The method of claim 14, wherein the contextual information comprises at least one of the user'"'"'s schedule and location data.

16. The method of claim 13, wherein the determining of the user'"'"'s topic of interest comprises, in response to the determination that the notification is provided, learning the determined user'"'"'s topic of interest based on the evaluated relevance.

17. The method of claim 13, wherein the determining of whether to provide a notification comprises generating text of the recognized speech and evaluating a relevance between the generated text and the user'"'"'s topic of interest.

18. The method of claim 17, wherein the evaluating of the relevance comprises applying at least one of support vector machine (SVM) classification or neural network classification to classify the generated text, and evaluating a relevance between a classification result and the user'"'"'s topic of interest.

19. The method of claim 17, wherein the evaluating of the relevance between the text and the user'"'"'s topic of interest is performed based on at least one of the following:

presence or absence of the user'"'"'s user keyword in the generated text, a number of user keywords in the text, or a number of words in the text relating to the user keyword.

20. The method of claim 12, wherein the notification message is outputted in at least one of the following forms:

text, a voice, a vibration, and an alerting sound.

21. The method of claim 12, wherein the producing of the notification message further comprises determining an importance of notification based on the speech recognition result and determining a notification method according to the importance.

22. The method of claim 12, further comprising:

translating a language of the recognized speech into a language designated by the user for evaluation of the relevance in the designated language, or to translating the notification into the designated language after evaluation of the relevance in the language of the recognized speech.

23. A method for selective notification, to a user, of detected relevant speech, comprising:

executing a processor to actuate a microphone;

storing, in a memory, speech captured by the microphone;

transforming the captured speech, via a voice recognizer, into text; and

,

selectively alerting a user, in response to a determined relation between the text and a pre-established user keyword.

24. The method of claim 23, further comprising:

generating a network of related words based on the pre-established user keyword; and

,

determining a relation between the text and the network of related words.

25. The method of claim 24, wherein the network is a neural network.

26. The method of claim 25, further comprising transforming one of the text or the user keyword from a first language into a second language for comparison to determine the relation between the text and the pre-established keyword.