US 8,509,931 B2Granted

Progressive encoding of audio

AssigneeGoogle Inc.

InventorsMatthew I. Lloyd, Martin Jansche

Life of this patent

Estimating the term…

Loading patent…

Abstract

The present disclosure includes processing a signal to generate a first sub-set of data, transmitting the first sub-set of data for generation of a reconstructed audio signal, the reconstructed audio signal having a fidelity relative to the signal, processing the signal to generate a second sub-set of data and a third sub-set of data, the second sub-set of data defining a second portion of the signal and comprising data that is different than data of the first sub-set of data, and the third sub-set of data defining a third portion of the signal and comprising data that is different than data of the first and second sub-sets of data, comparing a priority of the second sub-set of data to a priority of the third sub-set of data, and transmitting one of the second sub-set of data and the third sub-set of data over the network for improving the fidelity.

Claims25

Dependent claims

A system, comprising:

one or more computers;
and
a computer-readable medium coupled to the one or more computers and having instructions stored thereon which, when executed by the one or more computers, cause the one or more computers to perform operations comprising:
retrieving a digital audio signal;
processing the digital audio signal to generate a first sub-set of data, the first sub-set of data defining a first portion of the digital audio signal, the first sub-set of data represented as a first node in a direct acyclic graph;
transmitting the first sub-set of data for generation of a first version of a reconstructed audio signal, the first version of the reconstructed audio signal having a first fidelity relative to the digital audio signal;
receiving a first signal indicating that speech from the first version of the reconstructed audio signal was not recognized;
in response to receiving the first signal, processing the digital audio signal to generate a second sub-set of data and a third sub-set of data, the second sub-set of data defining a second portion of the digital audio signal and comprising data that is different than data of the first sub-set of data, and the third sub-set of data defining a third portion of the digital audio signal and comprising data that is different than data of the first and second sub-sets of data, the second and the third sub-set of data represented as a second and a third node, respectively, in the direct acyclic graph, the graph including edges between the first, the second, and the third nodes based on dependencies between the first, the second, and the third nodes;
comparing a priority of the second sub-set of data to a priority of the third sub-set of data, the comparing including:
identifying a particular node of the second and the third nodes for which each of the remaining nodes of the first, the second, and the third nodes that has an edge pointing to the particular node is previously transmitted;
transmitting, based on the identifying, at least one of the second sub-set of data and the third sub-set of data, wherein at least one of the second sub-set of data and the third sub-set of data is useable to obtain a second version of the reconstructed audio signal having a second fidelity relative to the digital audio signal, the second fidelity greater than the first fidelity;
receiving a second signal indicating that speech from the second version of the reconstructed audio signal was recognized;
and
in response to receiving the second signal, ceasing generation of subsequent sub-sets of data based on the digital audio signal.

11 more elements

A system, comprising:

one or more computers;
and
one or more computer-readable media coupled to the one or more computers and having instructions stored thereon which, when executed by the one or more computers, cause the one or more computers to perform operations comprising:
receiving a first sub-set of data, the first sub-set of data having been generated based on a digital audio signal, the first sub-set of data represented as a first node in a direct acyclic graph;
processing the first sub-set of data to generate a first version of a reconstructed audio signal, the first version of the reconstructed audio signal having a first fidelity relative to the digital audio signal;
determining that speech from the first version of the reconstructed audio signal was not recognized and, in response, transmitting a first signal for transmission of subsequent sub-sets of data;
receiving at least one of a second sub-set of data and a third sub-set of data based on a comparison of a priority of the second sub-set of data to a priority of the third sub-set of data, the second sub-set of data defining a second portion of the digital audio signal and comprising data that is different than data of the first sub-set of data, and the third sub-set of data defining a third portion of the digital audio signal and comprising data that is different than data of the first and second sub-sets of data, the second and the third sub-set of data represented as a second and a third node, respectively, in the direct acyclic graph, the graph including edges between the first, the second, and the third nodes based on dependencies between the first, the second, and the third nodes;
processing the at least one of the second sub-set of data and third sub-set of data, wherein at least one of the second sub-set of data and third sub-set of data is useable to obtain a second version of the reconstructed audio signal having a second fidelity relative to the digital audio signal, the second fidelity greater than the first fidelity;
and
determining that speech from the second version of the reconstructed audio signal was recognized and, in response, transmitting a second signal for ceasing generation of subsequent sub-sets of data based on the digital audio signal,
wherein receiving at least one of the second sub-set of data and the third sub-set of data includes receiving a particular node of the second and the third nodes for which each of the remaining nodes of the first, the second, and the third nodes that has an edge pointing to the particular node is previously transmitted.

8 more elements

A method, comprising:

receiving a first sub-set of data, the first sub-set of data having been generated based on a digital audio signal, the first sub-set of data represented as a first node in a direct acyclic graph;
processing the first sub-set of data to generate a first version of a reconstructed audio signal, the first version of the reconstructed audio signal having a first fidelity relative to the digital audio signal;
determining that speech from the first version of the reconstructed audio signal was not recognized and, in response, transmitting a first signal for transmission of subsequent sub-sets of data;
receiving at least one of a second sub-set of data and a third sub-set of data based on a comparison of a priority of the second sub-set of data to a priority of the third sub-set of data, the second sub-set of data defining a second portion of the digital audio signal and comprising data that is different than data of the first sub-set of data, and the third sub-set of data defining a third portion of the digital audio signal and comprising data that is different than data of the first and second sub-sets of data, the second and the third sub-set of data represented as a second and a third node, respectively, in the direct acyclic graph, the graph including edges between the first, the second, and the third nodes based on dependencies between the first, the second, and the third nodes;
processing the at least one of the second sub-set of data and third sub-set of data, wherein at least one of the second sub-set of data and third sub-set of data is useable to obtain a second version of the reconstructed audio signal having a second fidelity relative to the digital audio signal, the second fidelity greater than the first fidelity;
and
determining that speech from the second version of the reconstructed audio signal was recognized and, in response, transmitting a second signal for ceasing generation of subsequent sub-sets of data based on the digital audio signal,
wherein receiving at least one of the second sub-set of data and the third sub-set of data includes receiving a particular node of the second and the third nodes for which each of the remaining nodes of the first, the second, and the third nodes that has an edge pointing to the particular node is previously transmitted.

5 more elements

One or more non-transitory computer-readable media coupled to one or more computers and having instructions stored thereon which, when executed by the one or more computers, cause the one or more computers to perform operations comprising:

receiving a first sub-set of data, the first sub-set of data having been generated based on a digital audio signal, the first sub-set of data represented as a first node in a direct acyclic graph;
processing the first sub-set of data to generate a first version of a reconstructed audio signal, the first version of the reconstructed audio signal having a first fidelity relative to the digital audio signal;
determining that speech from the first version of the reconstructed audio signal was not recognized and, in response, transmitting a first signal for transmission of subsequent sub-sets of data;
receiving at least one of a second sub-set of data and a third sub-set of data based on a comparison of a priority of the second sub-set of data to a priority of the third sub-set of data, the second sub-set of data defining a second portion of the digital audio signal and comprising data that is different than data of the first sub-set of data, and the third sub-set of data defining a third portion of the digital audio signal and comprising data that is different than data of the first and second sub-sets of data, the second and the third sub-set of data represented as a second and a third node, respectively, in the direct acyclic graph, the graph including edges between the first, the second, and the third nodes based on dependencies between the first, the second, and the third nodes;
processing the at least one of the second sub-set of data and third sub-set of data, wherein at least one of the second sub-set of data and third sub-set of data is useable to obtain a second version of the reconstructed audio signal having a second fidelity relative to the digital audio signal, the second fidelity greater than the first fidelity;
and
determining that speech from the second version of the reconstructed audio signal was recognized and, in response, transmitting a second signal for ceasing generation of subsequent sub-sets of data based on the digital audio signal,
wherein receiving at least one of the second sub-set of data and the third sub-set of data includes receiving a particular node of the second and the third nodes for which each of the remaining nodes of the first, the second, and the third nodes that has an edge pointing to the particular node is previously transmitted.

5 more elements

Dependencies are inferred from the claim text.

Facts

Application: 13/250,576Filed 30 Sep 2011 · continuation
Priority: 30 Sep 2010
Published: US 2012/0083910 A15 Apr 2012
Granted: 13 Aug 2013
Term ends: Not estimatedThe source records don’t support an estimate.

Classification4 codes

G10L 15/20
Speech recognition: speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech
G10L 15/18
Speech classification or search: using natural language modelling
G10L 2015/223
Procedures used during a speech recognition process, e.g. man-machine dialogue: execution procedure of a spoken command
G10L
Speech analysis techniques or speech synthesis

Family

Application12/895,258Parent of this continuation · filed 30 Sep 2010
US 2012/0084089 A1Pre-grant publication · published 5 Apr 2012
US 2012/0083910 A1Published application
US 8,965,545 B2Related patent
US 8,509,931 B2This patent

From the US filing history. Foreign family members aren’t listed.