Systems, vehicles, and methods for limiting speech-based access to an audio metadata database

• US 9,620,148 B2
• Filed: 07/01/2013
• Issued: 04/11/2017
• Est. Priority Date: 07/01/2013
• Status: Active Grant

• Current Assignee: Toyota Jidosha Kabushiki Kaisha (Toyota Motor Corporation)
• Original Assignee: Toyota Motor Engineering & Manufacturing North America Incorporated (Toyota Motor Corporation)
• Inventors: Schmidt, Eric Randell
• Primary Examiner(s): Lerner, Martin
• Application Number:
  US13/932,264
• Publication Number:
  US 20150006165A1
• Time in Patent Office: 1,380 Days
• Field of Search: 704251, 704275, 711171, 711172, 725 45, 707662
• CPC Class Codes: G10L 15/285 Memory allocation or algorithm optimisation to reduce hardware requirements
• CPC Class Codes: G10L 25/54 for retrieval

Abstract

Systems, vehicles, and methods for limiting speech-based access to an audio metadata database are described herein. Audio metadata databases described herein include a plurality of audio metadata entries. Each audio metadata entry includes metadata information associated with at least one audio file. Embodiments described herein determine when a size of the audio metadata database reaches a threshold size, and limit which of the plurality of audio metadata entries may be accessed in response to the speech input signal when the size of the audio metadata database reaches the threshold size.

Claims

1. A speech recognition system comprising:

one or more processors;

a microphone communicatively coupled to the one or more processors, wherein the microphone receives acoustic vibrations;

one or more memory modules communicatively coupled to the one or more processors;

an audio metadata database stored in the one or more memory modules, wherein the audio metadata database includes a plurality of audio metadata entries, wherein each audio metadata entry includes metadata information associated with at least one audio file, wherein the plurality of audio metadata entries includes a first audio metadata entry associated with a first audio file; and

machine readable instructions stored in the one or more memory modules that cause the speech recognition system to perform at least the following when executed by the one or more processors;

transform the acoustic vibrations received by the microphone into a speech input signal;

determine a size of the audio metadata database;

allow speech-based access to the first audio metadata entry in response to the speech input signal when the size of the audio metadata database is less than a threshold size; and

remove speech-based access to the first audio metadata entry in response to the speech input signal when the size of the audio metadata database reaches the threshold size,

wherein;

the plurality of audio metadata entries includes a first group of audio metadata entries and a second group of audio metadata entries;

the first group of audio metadata entries is associated with a first group of audio files that are associated with a first audio source device;

the second group of audio metadata entries is associated with a second group of audio files that are associated with a second audio source device; and

the machine readable instructions stored in the one or more memory modules cause the speech recognition system to perform at least the following when executed by the one or more processors;

allow speech-based access to the first group of audio metadata entries associated with the first group of audio files that are associated with the first audio source device when the size of the audio metadata database is less than the threshold size;

allow speech-based access to the second group of audio metadata entries associated with the second group of audio files that are associated with the second audio source device when the size of the audio metadata database is less than the threshold size;

allow speech-based access to the first group of audio metadata entries associated with the first group of audio files that are associated with the first audio source device when the size of the audio metadata database reaches the threshold size; and

remove speech-based access to the second group of audio metadata entries associated with the second group of audio files that are associated with the second audio source device when the size of the audio metadata database reaches the threshold size.

2. The speech recognition system of claim 1, wherein the machine readable instructions stored in the one or more memory modules cause the speech recognition system to perform at least the following when executed by the one or more processors:

determine a number of audio metadata entries in the audio metadata database; and

determine the size of the audio metadata database reaches the threshold size when the number of audio metadata entries in the audio metadata database reaches a threshold number.

3. The speech recognition system of claim 1, wherein the machine readable instructions stored in the one or more memory modules cause the speech recognition system to perform at least the following when executed by the one or more processors:

determine a memory size of the audio metadata database; and

determine the size of the audio metadata database reaches the threshold size when the memory size of the audio metadata database reaches a threshold memory size.

4. The speech recognition system of claim 1, wherein:

the plurality of audio metadata entries includes a first category group of audio metadata entries and a second category group of audio metadata entries;

the first category group of audio metadata entries are associated with a first metadata category;

the second category group of audio metadata entries are associated with a second metadata category different from the first metadata category; and

the machine readable instructions stored in the one or more memory modules cause the speech recognition system to perform at least the following when executed by the one or more processors;

allow speech-based access to the first category group of audio metadata entries associated with the first metadata category when the size of the audio metadata database is less than the threshold size;

allow speech-based access to the second category group of audio metadata entries associated with the second metadata category when the size of the audio metadata database is less than the threshold size;

allow speech-based access to the first category group of audio metadata entries associated with the first metadata category when the size of the audio metadata database reaches the threshold size; and

remove speech-based access to the second category group of audio metadata entries associated with the second metadata category when the size of the audio metadata database reaches the threshold size.

5. The speech recognition system of claim 1, wherein the plurality of audio metadata entries includes a category group of audio metadata entries, wherein the category group of audio metadata entries are associated with a metadata category, wherein the machine readable instructions stored in the one or more memory modules cause the speech recognition system to perform at least the following when executed by the one or more processors:

remove the category group of audio metadata entries from the plurality of audio metadata entries that may be accessed in response to the speech input signal when the size of the audio metadata database reaches the threshold size.

6. The speech recognition system of claim 1, wherein the machine readable instructions stored in the one or more memory modules cause the speech recognition system to perform at least the following when executed by the one or more processors:

limit which of the plurality of audio metadata entries may be accessed in response to the speech input signal based on an audio source associated with at least one of the plurality of audio metadata entries when the size of the audio metadata database reaches the threshold size.

7. The speech recognition system of claim 6, wherein the plurality of audio metadata entries includes an audio source group of audio metadata entries, wherein the audio source group of audio metadata entries are associated with an audio source, wherein the machine readable instructions stored in the one or more memory modules cause the speech recognition system to perform at least the following when executed by the one or more processors:

remove at least one of the audio source group of audio metadata entries from the plurality of audio metadata entries that may be accessed in response to the speech input signal when the size of the audio metadata database reaches the threshold size.

8. The speech recognition system of claim 6, wherein the plurality of audio metadata entries includes an audio source group of audio metadata entries, wherein the audio source group of audio metadata entries are associated with an audio source, wherein the machine readable instructions stored in the one or more memory modules cause the speech recognition system to perform at least the following when executed by the one or more processors:

remove the audio source group of audio metadata entries from the plurality of audio metadata entries that may be accessed in response to the speech input signal when the size of the audio metadata database reaches the threshold size.

9. The speech recognition system of claim 1, wherein the metadata information includes a song title, an album name, an artist, a composer, a playlist, a genre, an audiobook name, or a podcast title.

10. The speech recognition system of claim 1, wherein the machine readable instructions stored in the one or more memory modules cause the speech recognition system to perform at least the following when executed by the one or more processors:

remove a speech recognition grammar associated with the first audio metadata entry from memory in response to removing speech-based access to the first audio metadata entry when the size of the audio metadata database reaches the threshold size.

11. A vehicle comprising:

one or more processors;

a microphone communicatively coupled to the one or more processors, wherein the microphone receives acoustic vibrations;

one or more memory modules communicatively coupled to the one or more processors;

an audio metadata database stored in the one or more memory modules, wherein the audio metadata database includes a plurality of audio metadata entries, wherein each audio metadata entry includes metadata information associated with at least one audio file, wherein the plurality of audio metadata entries includes a first audio metadata entry associated with a first audio file; and

machine readable instructions stored in the one or more memory modules that cause the vehicle to perform at least the following when executed by the one or more processors;

transform the acoustic vibrations received by the microphone into a speech input signal;

determine a size of the audio metadata database;

allow speech-based access to the first audio metadata entry in response to the speech input signal when the size of the audio metadata database is less than a threshold size; and

remove speech-based access to the first audio metadata entry in response to the speech input signal when the size of the audio metadata database reaches the threshold size,

wherein;

the plurality of audio metadata entries includes a first group of audio metadata entries and a second group of audio metadata entries;

the first group of audio metadata entries is associated with a first group of audio files that are associated with a first audio source device;

the second group of audio metadata entries is associated with a second group of audio files that are associated with a second audio source device; and

the machine readable instructions stored in the one or more memory modules cause the vehicle to perform at least the following when executed by the one or more processors;

allow speech-based access to the first group of audio metadata entries associated with the first group of audio files that are associated with the first audio source device when the size of the audio metadata database is less than the threshold size;

allow speech-based access to the second group of audio metadata entries associated with the second group of audio files that are associated with the second audio source device when the size of the audio metadata database is less than the threshold size;

allow speech-based access to the first group of audio metadata entries associated with the first group of audio files that are associated with the first audio source device when the size of the audio metadata database reaches the threshold size; and

remove speech-based access to the second group of audio metadata entries associated with the second group of audio files that are associated with the second audio source device when the size of the audio metadata database reaches the threshold size.

12. The vehicle of claim 11, wherein the machine readable instructions stored in the one or more memory modules cause the vehicle to perform at least the following when executed by the one or more processors:

determine a number of audio metadata entries in the audio metadata database; and

determine the size of the audio metadata database reaches the threshold size when the number of audio metadata entries in the audio metadata database reaches a threshold number.

13. The vehicle of claim 11, wherein the machine readable instructions stored in the one or more memory modules cause the vehicle to perform at least the following when executed by the one or more processors:

limit which of the plurality of audio metadata entries may be accessed in response to the speech input signal based on a metadata category associated with at least one of the plurality of audio metadata entries when the size of the audio metadata database reaches the threshold size.

14. The vehicle of claim 11, wherein the machine readable instructions stored in the one or more memory modules cause the vehicle to perform at least the following when executed by the one or more processors:

limit which of the plurality of audio metadata entries may be accessed in response to the speech input signal based on an audio source associated with at least one of the plurality of audio metadata entries when the size of the audio metadata database reaches the threshold size.

15. The vehicle of claim 11, wherein the machine readable instructions stored in the one or more memory modules cause the vehicle to perform at least the following when executed by the one or more processors:

store the audio metadata database in the one or more memory modules before the vehicle is powered off; and

access the audio metadata database from the one or more memory modules when the vehicle is turned on.

16. The vehicle of claim 11, wherein the machine readable instructions stored in the one or more memory modules cause the vehicle to perform at least the following when executed by the one or more processors:

remove a speech recognition grammar associated with the first audio metadata entry from memory in response to removing speech-based access to the first audio metadata entry when the size of the audio metadata database reaches the threshold size.

17. A method for limiting access to an audio metadata database stored in one or more memory modules, wherein the audio metadata database includes a plurality of audio metadata entries, wherein each audio metadata entry includes metadata information associated with at least one audio file, wherein the plurality of audio metadata entries includes a first audio metadata entry associated with a first audio file, the method comprising:

receiving, automatically by a processor a speech input signal;

determining a size of the audio metadata database;

allowing speech-based access to the first audio metadata entry in response to the speech input signal when the size of the audio metadata database is less than a threshold size; and

removing speech-based access to the first audio metadata entry in response to the speech input signal when the size of the audio metadata database reaches the threshold size,

wherein the plurality of audio metadata entries includes a first group of audio metadata entries and a second group of audio metadata entries, the first group of audio metadata entries is associated with a first group of audio files that are associated with a first audio source device, and the second group of audio metadata entries is associated with a second group of audio files that are associated with a second audio source device, the method further comprising;

allowing speech-based access to the first group of audio metadata entries associated with the first group of audio files that are associated with the first audio source device when the size of the audio metadata database is less than the threshold size;

allowing speech-based access to the second group of audio metadata entries associated with the second group of audio files that are associated with the second audio source device when the size of the audio metadata database is less than the threshold size;

allowing speech-based access to the first group of audio metadata entries associated with the first group of audio files that are associated with the first audio source device when the size of the audio metadata database reaches the threshold size; and

removing speech-based access to the second group of audio metadata entries associated with the second group of audio files that are associated with the second audio source device when the size of the audio metadata database reaches the threshold size.

18. The method of claim 17, further comprising:

determining a number of audio metadata entries in the audio metadata database; and

determining the size of the audio metadata database reaches the threshold size when the number of audio metadata entries in the audio metadata database reaches a threshold number.

19. The method of claim 17, further comprising:

limiting which of the plurality of audio metadata entries may be accessed in response to the speech input signal based on a metadata category associated with at least one of the plurality of audio metadata entries when the size of the audio metadata database reaches the threshold size.

20. The method of claim 17, further comprising:

limiting which of the plurality of audio metadata entries may be accessed in response to the speech input signal based on an audio source associated with at least one of the plurality of audio metadata entries when the size of the audio metadata database reaches the threshold size.

21. The method of claim 17, wherein the metadata information includes a song title, an album name, an artist, a composer, a playlist, a genre, an audiobook name, or a podcast title.

22. The method of claim 17, further comprising:

removing a speech recognition grammar associated with the first audio metadata entry from memory in response to removing speech-based access to the first audio metadata entry when the size of the audio metadata database reaches the threshold size.