Daily cognitive monitoring of early signs of hearing loss

Patent metadata

Field	Value
Publication number	US-10238333-B2
Application number	US-201615236064-A
Country	US
Kind code	B2
Filing date	Aug 12, 2016
Priority date	Aug 12, 2016
Publication date	Mar 26, 2019
Grant date	Mar 26, 2019

Abstract

In one embodiment, a computer program product includes a computer readable storage medium having program instructions embodied therewith. The embodied program instructions are executable by a processing circuit to cause the processing circuit to receive collected data from one or more data collection devices. The collected data is aggregated over a period of time lasting at least one month, and the collected data includes audio data of a user of the one or more data collection devices. The embodied program instructions also cause the processing circuit to store the audio data to a computer readable storage medium. Moreover, the embodied program instructions cause the processing circuit to analyze the audio data for indications of hearing loss in the user over the period of time.

First claim

What is claimed is:

1. A system, comprising:
a processing circuit and logic integrated with the processing circuit, executable by the processing circuit, or integrated with and executable by the processing circuit, the logic being configured to cause the processing circuit to:
obtain baseline hearing ability for a user;
receive collected data from one or more data collection devices after obtaining the baseline hearing, the collected data being aggregated over a period of time lasting at least one month, wherein the collected data comprises audio data of the user of the one or more data collection devices;
analyze the audio data for indications of hearing loss in the user over the period of time, wherein the logic configured to cause the processing circuit to analyze the audio data comprises logic configured to cause the processing circuit to:
determine whether an emotion of the user and/or at least one noise caused an elevated speech volume, wherein the emotion is determined based on a trait not utilized during normal speaking, and wherein the trait is selected from the group consisting of: a cracking voice of the user, an emphasis on words that indicate the emotion, an emphasis on words that indicate the emotion, an emphasis on parts of words that indicate the emotion, and combinations thereof;
identify the at least one noise from the audio data, the at least one noise being selected from the group consisting of: background noise, ambient noise, and combinations thereof; and
normalize the audio data to account for the emotion of the user and the identified at least one noise, and discount the elevated speech volume accordingly, prior to storing the audio data to a computer readable storage medium; and

analyze the stored audio data for one or more indicia of hearing loss; and
alert the user of the one or more indicia of hearing loss being detected in response to determining hearing loss that exceeds a predetermined threshold percentage of the baseline hearing.

2. The system as recited in claim 1 , wherein the logic is further configured to cause the processing circuit to:
determine metadata about the audio data, the metadata comprising at least an identification of the user and a timestamp for the audio data; and
store the metadata with the audio data as a tuple having two or more values.

3. The system as recited in claim 2 , wherein the metadata further comprises a tally of a number of times that the user requested for spoken dialog to be repeated over a plurality of periods of time, and wherein an increasing tally of the number of times that the user requested for spoken dialog to be repeated over several time periods is indicative of hearing loss occurring; and
wherein the logic is further configured to cause the processing circuit to quantify an amount of the hearing loss experienced by the user over a predetermined amount of time.

4. The system as recited in claim 1 , wherein the audio data is selected from the group consisting of: a conversation in which the user participated, a telephone call received or initiated by the user, playback of recorded audio content listened to by the user, and combinations thereof.

5. The system as recited in claim 1 , wherein the one or more data collection devices are selected from the group consisting of: a mobile telephone, a smartwatch, a tablet, a digital wearable assistant, a portable audio playback device, and combinations thereof.

6. The system as recited in claim 1 , wherein the threshold percentage is about 90% of the baseline hearing ability of the user.

7. The system as recited in claim 1 , wherein the logic is further configured to cause the processing circuit to:
determine metadata about the audio data, the metadata comprising at least an identification of the user and a timestamp for the audio data;
store the metadata with the audio data as a tuple having two or more values, wherein the metadata further comprises a tally of a number of times that the user requested for spoken dialog to be repeated over a plurality of periods of time, and wherein an increasing tally of the number of times that the user requested for spoken dialog to be repeated over several time periods is indicative of hearing loss occurring;
perform regression analysis on the audio data to determine indications of hearing loss in the user over the period of time;
wherein the audio data is selected from the group consisting of: a conversation in which the user participated, a telephone call received or initiated by the user, playback of recorded audio content listened to by the user, and combinations thereof;
wherein the one or more data collection devices are selected from the group consisting of: a mobile telephone, a smartwatch, a tablet, a digital wearable assistant, a portable audio playback device, and combinations thereof; and
wherein the computer readable storage medium is located remotely from the one or more data collection devices.

8. A computer program product, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the embodied program instructions being executable by a processing circuit to cause the processing circuit to:
obtain, by the processing circuit, baseline hearing for a user;
receive, by the processing circuit, collected data from one or more data collection devices after obtaining the baseline hearing, the collected data being aggregated over a period of time lasting at least one month, wherein the collected data comprises audio data of the user of the one or more data collection devices;
analyze, by the processing circuit, the audio data for indications of hearing loss in the user over the period of time, wherein the program instructions configured to cause the processing circuit to analyze the audio data comprises program instructions configured to cause the processing circuit to:
determine, using the processing circuit, whether an emotion of the user and/or at least one noise caused an elevated speech volume, wherein the emotion is determined based on a trait not utilized during normal speaking, and wherein the trait is selected from the group consisting of: a cracking voice of the user, an emphasis on words that indicate the emotion, an emphasis on words that indicate the emotion, an emphasis on parts of words that indicate the emotion, and combinations thereof;
identify, using the processing circuit, the at least one noise from the audio data, the at least one noise being selected from the group consisting of: background noise, ambient noise, and combinations thereof; and
normalize, using the processing circuit, the audio data to account for the emotion of the user and the identified at least one noise, and discount the elevated speech volume accordingly, prior to storing the audio data to the computer readable storage medium; and

analyze, using the processing circuit, the stored audio data for one or more indicia of hearing loss; and
alert, by the processing circuit, the user of the one or more indicia of hearing loss being detected in response to determining hearing loss that exceeds a predetermined threshold percentage of the baseline hearing being detected as a result of analyzing the audio data.

9. The computer program product as recited in claim 8 , wherein the embodied program instructions are further executable by the processing circuit to cause the processing circuit to:
determine, by the processing circuit, metadata about the audio data; and
store, by the processing circuit, the metadata with the audio data as a tuple having two or more values,
wherein the metadata comprises an identification of the user, a timestamp for the audio data, a speaking volume of the user during a convers

Assignees

• IBM

Inventors

• Hwang Inseok
• Liu Su
• Rozner Eric J
• Sze Chin Ngai

Classifications

• A61B5/7264

  Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems · CPC title

• A61B2562/0204

  Acoustic sensors · CPC title

• A61B5/6898

  Portable consumer electronic devices, e.g. music players, telephones, tablet computers · CPC title

• G10L25/21

  the extracted parameters being power information · CPC title

• A61B5/7203

  for noise prevention, reduction or removal · CPC title