Performing automated voice operations based on sensor data reflecting sound vibration conditions and motion conditions
First Claim
Patent Images
1. A wearable device comprising:
- an air-based microphone;
a bone conduction microphone; and
logic, implemented at least partly in fixed-functionality hardware, to;
determine a sound vibration condition of an ambient environment of the wearable device based at least in part on a signal associated with the air-based microphone,determine a motion condition of the wearable device based at least in part on a signal associated with the bone conduction microphone, andperform one or more of a plurality of automated voice operations based at least in part on the sound vibration condition and the motion condition, wherein the plurality of automated voice operations are to be arranged in order of progressively higher power domains,wherein one of the plurality of automated voice operations is a speaker verification operation that is to be activated based on a detection of a key phrase by the air-based microphone and a specific vibratory motion signature associated with the key phrase by the bone conduction microphone, andwherein, when the speaker verification operation is activated, a subsequent voice operation from the plurality of automated voice operations is to be activated if the air-based microphone detects that an identified key phrase was spoken by a known speaker and the bone conduction microphone detects a vibratory motion signature associated with the known speaker.
1 Assignment
0 Petitions
Accused Products
Abstract
Systems and methods may provide for determining a sound vibration condition of an ambient environment of a wearable device and determining a motion condition of the wearable device. In addition, one or more automated voice operations may be performed based at least in part on the sound vibration condition and the motion condition. In one example, two or more signals corresponding to the sound vibration condition and the motion condition may be combined.
31 Citations
15 Claims
-
1. A wearable device comprising:
-
an air-based microphone; a bone conduction microphone; and logic, implemented at least partly in fixed-functionality hardware, to; determine a sound vibration condition of an ambient environment of the wearable device based at least in part on a signal associated with the air-based microphone, determine a motion condition of the wearable device based at least in part on a signal associated with the bone conduction microphone, and perform one or more of a plurality of automated voice operations based at least in part on the sound vibration condition and the motion condition, wherein the plurality of automated voice operations are to be arranged in order of progressively higher power domains, wherein one of the plurality of automated voice operations is a speaker verification operation that is to be activated based on a detection of a key phrase by the air-based microphone and a specific vibratory motion signature associated with the key phrase by the bone conduction microphone, and wherein, when the speaker verification operation is activated, a subsequent voice operation from the plurality of automated voice operations is to be activated if the air-based microphone detects that an identified key phrase was spoken by a known speaker and the bone conduction microphone detects a vibratory motion signature associated with the known speaker. - View Dependent Claims (2, 3, 4)
-
-
5. A method comprising:
-
determining a sound vibration condition of an ambient environment of a wearable device based at least in part on a signal associated with an air-based microphone; determining a motion condition of the wearable device based at least in part on a signal associated with a bone conduction microphone; performing one or more of a plurality of automated voice operations based at least in part on the sound vibration condition and the motion condition, wherein the plurality of automated voice operations are arranged in order of progressively higher power domains; activating a speaker verification operation from the plurality of automated voice operations based on a detection of a key phrase by the air-based microphone and a specific vibratory motion signature associated with the key phrase by the bone conduction microphone; and activating a subsequent voice operation from the plurality of automated voice operations when the speaker verification operation is activated and when the speaker verification operation determines that the air-based microphone detects that an identified key phrase was spoken by a known speaker and the bone conduction microphone detects a vibratory motion signature associated with the known speaker. - View Dependent Claims (6, 7)
-
-
8. At least one non-transitory computer readable storage medium comprising a set of instructions which, if executed by a wearable device, cause the wearable device to:
-
determine a sound vibration condition of an ambient environment of the wearable device based at least in part on a signal associated with an air-based microphone; determine a motion condition of the wearable device based at least in part on a signal associated with a bone conduction microphone; perform one or more of a plurality of automated voice operations based at least in part on the sound vibration condition and the motion condition, wherein the plurality of automated voice operations are to be arranged in order of progressively higher power domains; activate a speaker verification operation from the plurality of automated voice operations based on a detection of a key phrase by the air-based microphone and a specific vibratory motion signature associated with the key phrase by the bone conduction microphone; and activate a subsequent voice operation from the plurality of automated voice operations when the speaker verification operation is activated and when the speaker verification operation determines that the air-based microphone detects that an identified key phrase was spoken by a known speaker and the bone conduction microphone detects a vibratory motion signature associated with the known speaker. - View Dependent Claims (9, 10, 11)
-
-
12. An apparatus comprising:
-
logic, implemented at least partly in fixed-functionality hardware, to; determine a sound vibration condition of an ambient environment of a wearable device based at least in part on a signal associated with an air-based microphone, determine a motion condition of the wearable device based at least in part on a signal associated with a bone conduction microphone, and perform one or more of a plurality of automated voice operations based at least in part on the sound vibration condition and the motion condition, wherein the plurality of the automated voice operations are to be arranged in order of progressively higher power domains, wherein one of the plurality of automated voice operations is a speaker verification operation that is to be activated based on a detection of a key phrase by the air-based microphone and a specific vibratory motion signature associated with the key phrase by the bone conduction microphone, and wherein, when the speaker verification operation is activated, a subsequent voice operation from the plurality of automated voice operations is to be activated if the air-based microphone detects that an identified key phrase was spoken by a known speaker and the bone conduction microphone detects a vibratory motion signature associated with the known speaker. - View Dependent Claims (13, 14, 15)
-
Specification