Facilitating creation and playback of user-recorded audio

Patent metadata

Field	Value
Publication number	US-11238854-B2
Application number	US-201615378920-A
Country	US
Kind code	B2
Filing date	Dec 14, 2016
Priority date	Dec 14, 2016
Publication date	Feb 1, 2022
Grant date	Feb 1, 2022

Abstract

Methods, apparatus, and computer readable media are described related to recording, organizing, and making audio files available for consumption by voice-activated products. In various implementations, in response to receiving an input from a first user indicating that the first user intends to record audio content, audio content may be captured and stored. Input may be received from the first user indicating at least one identifier for the audio content. The stored audio content may be associated with the at least one identifier. A voice input may be received from a subsequent user. In response to determining that the voice input has particular characteristics, speech recognition may be biased in respect of the voice input towards recognition of the at least one identifier. In response to recognizing, based on the biased speech recognition, presence of the at least one identifier in the voice input, the stored audio content may be played.

First claim

What is claimed is:

1. A method comprising:
in response to receiving an input from a first user indicating that the first user intends to record audio content targeted towards one or more children, causing capture and storage of audio content in a library of one or more recorded audio files;
receiving input from the first user indicating at least one bibliographic word or phrase that identifies the audio content;
associating the stored audio content with the at least one bibliographic word or phrase in the library of one or more recorded audio files;
receiving a voice input from a subsequent user;
analyzing characteristics of the voice input;
detecting one or more characteristics of the voice input;
determining, based on the detected one or more characteristics, that the subsequent user is a child;
in response to determining that the subsequent user is a child, biasing speech recognition in respect of the voice input towards recognition of one or more bibliographic words or phrases associated with one or more stored audio files in the library that were recorded for one or more children, wherein the one or more bibliographic words or phrases include the at least one identifier;
recognizing, based on the biased speech recognition, the at least one bibliographic word or phrase in the voice input;
searching the library based on the recognized at least one bibliographic word or phrase to locate the stored audio content; and
causing playback of the stored audio content.

2. The method of claim 1 , further comprising:
in response to receiving the input from the first user indicating that the first user intends to record audio content, providing a prompt to the first user instructing the first user to provide the input indicating the at least one bibliographic word or phrase.

3. A computer-implemented method, comprising:
receiving, by a voice-activated product at one or more input devices, a first command from a user, wherein the first command notifies the voice-activated product that the user wishes to record an audible rendition of a narrative targeted towards one or more children;
receiving, by the voice-activated product at one or more of the input devices, bibliographic input from the user, wherein the bibliographic input is indicative of bibliographic information associated with the narrative;
recording, by the voice-activated product via an audio input device, the audible rendition of the narrative spoken by the user;
storing, in computer memory available to the voice-activated product, an audio file comprising the recorded audible rendition of the narrative spoken by the user, wherein the audio file is indexed in the computer memory based at least in part on the bibliographic information;
receiving, by the voice activated product at one or more of the input devices, a voice input from a subsequent user;
detecting one or more characteristics of the voice input;
determining, based on the detected one or more characteristics, that the subsequent user is a child;
in response to determining that the subsequent user is a child, biasing speech recognition in respect of the voice input towards recognition of one or more bibliographic identifiers associated with one or more stored audio files that were recorded for one or more children, wherein the one or more bibliographic identifiers include the bibliographic information associated with the narrative;
recognizing in the voice input, based on the biased speech recognition, the bibliographic information associated with the narrative;
searching the computer memory based on the recognized bibliographic information to locate the stored audio file; and
rendering, by the voice-activated product via an audio output device, the audio file.

4. The computer-implemented method of claim 3 , wherein the first command comprises speech received via the audio input device.

5. The computer-implemented method of claim 3 , further comprising providing, by the voice-activated product at one or more output devices, a solicitation for the bibliographic information associated with the narrative.

6. The computer-implemented method of claim 3 , wherein the bibliographic input comprises speech received via the audio input device.

7. The computer-implemented method of claim 3 , wherein the narrative comprises a preexisting written work, and the method further comprises matching the bibliographic information to the preexisting written work in a database.

8. The computer-implemented method of claim 7 , further comprising providing, by the voice-activated product via one or more of the output devices, additional information associated with the preexisting written work in the database.

9. The computer-implemented method of claim 8 , wherein the additional information includes a visual rendition representing the preexisting written work.

10. The computer-implemented method of claim 7 , wherein the audio file is further indexed in the computer memory based on additional information associated with the preexisting written work in the database.

11. The computer-implemented method of claim 3 , wherein the computer-memory stores a plurality of recorded audio files that are indexed by corresponding bibliographic information.

12. The computer-implemented method of claim 11 , wherein the plurality of audio files are further indexed by identities of users that recorded them.

13. The computer-implemented method of claim 3 , further comprising incorporating, by the voice-activated product into the audio file, one or more sound effects selected by the user.

14. The computer-implemented method of claim 3 , further comprising initiating, by the voice-activated product, an interactive dialog tailored towards the child.

15. A voice-enabled device comprising:
one or more processors;
one or more speakers operably coupled with the one or more processors;
one or more microphones operably coupled with the one or more processors; and
memory operably coupled with the one or more processors, wherein the memory stores instructions that, in response to execution of the instructions by the one or more processors, cause the one or more processors to:
receive, at one or more of the microphones, a first command from a user, wherein the first command indicates that the user wishes to record an audible rendition of a narrative, wherein the narrative comprises a preexisting written work;
receive, at one or more of the microphones devices, bibliographic input from the user, wherein the bibliographic input is indicative of bibliographic information associated with the narrative;
record, via one or more of the microphones, the audible rendition of the narrative spoken by the user;
match the bibliographic information to the preexisting written work in a database, wherein additional information is associated with the preexisting written work in the database;
store, in the memory or in computer memory of one or more remote computing devices, an audio file comprising the recorded audible rendition of the narrative spoken by the user, wherein the audio file is indexed based at least in part on the bibliographic information;
receive, at one or more of the microphones, a voice input from a subsequent user;
detect one or more characteristics of the voice input;
determine, based on the detected one or more characteristics, that the subsequent user is a child;
in response to the determination that the subsequent user is a child, bias speech recognition in respect of the voice input towards recognition of the additional information associated with the preexisting written work in the database;
recognize in the

Assignees

• Google Llc

Inventors

• Aggarwal Vikram
• James Barnaby

Classifications

• G10L2015/088

  Word spotting · CPC title

• G10L25/51

  for comparison or discrimination · CPC title

• G10L15/08

  Speech classification or search · CPC title

• G10L15/02

  Feature extraction for speech recognition; Selection of recognition unit · CPC title

• G06F40/253

  Grammatical analysis; Style critique · CPC title