Granted Patent B2

US 12,374,340 · App. 17/806,286 · Granted Jul 29, 2025

Inventors: Ethan S. Headings (Columbus, OH); Feng-wei Chen (Cary, NC); Neha S Deshpande (Cary, NC); Madhavi Kolachala (Cary, NC)

Assignee: International Business Machines Corporation

G10L17/22G10L17/02G10L17/06G10L25/78

Abstract

Claims (59)

1. A computer-implemented method for determining a name of an individual based on voice detection, the computer-implemented method comprising:

receiving, by an audio input device, an audio input associated with a conversation between a user and the individual;

recording, by the audio input device, the received audio input;

determining voice characteristics of a voice of the individual based on the recorded audio input, wherein the audio input includes a decibel level of the conversation;

instructing, based on the decibel level of the conversation, the audio input device to change from a passive state to an active state;

determining that an amity level of the conversation is greater than a threshold value, wherein

the amity level is one of an acquaintance or a friend, and

the amity level is determined based on:

the instructing of the audio input device to change from the passive state to the active state; and

contextual information associated with specific words or phrases used in the conversation, the voice characteristics of the individual, and at least one of frequency of meetings between the user and the individual, a time since previous meeting between the user and the individual, or a time since first meeting between the user and the individual;

comparing, based on the determination that the amity level is greater than the threshold value, the voice characteristics of the voice of the individual to voice characteristics of voice profiles;

as a result of the voice and one of the voice profiles meeting a similarity threshold, determining the name associated with one of the voice profiles; and

providing the name to the user who is having the conversation with the individual.

2. The computer-implemented method of claim 1 , further comprising:

monitoring an audio space in proximity to the user; and

detecting a presence of speech in the audio input captured in the audio space, wherein the speech is associated with the conversation.

3. The computer-implemented method of claim 2 , further comprising

determining whether the conversation includes a named greeting, the named greeting being an utterance from one of the users or the individual including the name of the individual, wherein the voice characteristics are determined as a result of the named greeting being absent in the conversation.

4. The computer-implemented method of claim 1 , wherein the voice characteristics include a tone, a pitch, and a dialect.

5. A computer-readable storage media that configures a computer to perform program instructions stored on the computer-readable storage media for determining a name of an individual based on voice detection, the program instructions comprising:

receiving, by an audio input device, an audio input associated with a conversation between a user and the individual;

recording, by the audio input device, the received audio input;

determining voice characteristics of a voice of the individual based on the recorded audio input, wherein the audio input includes a decibel level of the conversation;

instructing, based on the decibel level of the conversation, the audio input device to change from a passive state to an active state;

determining that an amity level of the conversation is greater than a threshold value, wherein

the amity level is one of an acquaintance or a friend, and

the amity level is determined based on:

the instructing of the audio input device to change from the passive state to the active state; and

contextual information associated with specific words or phrases used in the conversation, the voice characteristics of the individual, and at least one of frequency of meetings between the user and the individual, a time since previous meeting between the user and the individual, or a time since first meeting between the user and the individual;

comparing, based on the determination that the amity level is greater than the threshold value, the voice characteristics of the voice of the individual to voice characteristics of voice profiles;

as a result of the voice and one of the voice profiles meeting a similarity threshold, determining the name associated with one of the voice profiles; and

providing the name to the user who is having the conversation with the individual.

6. The computer-readable storage media of claim 5 , wherein the program instructions further comprise:

monitoring an audio space in proximity to the user; and

detecting a presence of speech in the audio input captured in the audio space, wherein the speech is associated with the conversation.

7. The computer-readable storage media of claim 6 , wherein the program instructions further comprise:

determining whether the conversation includes a named greeting, the named greeting being an utterance from one of the users or the individual including the name of the individual, wherein the voice characteristics are determined as a result of the named greeting being absent in the conversation.

8. The computer-readable storage media of claim 5 , wherein the voice characteristics include a tone, a pitch, and a dialect.

9. A computer system to determine a name of an individual based on voice detection, the computer system comprising:

one or more computer processors;

one or more computer-readable storage media; and

program instructions stored on the one or more of the computer-readable storage media, the program instructions executable by at least one processor of the one or more computer processors to cause the at least one processor;

receive, by an audio input device, an audio input associated with a conversation between a user and the individual;

record, by the audio input device, the received audio input;

determine voice characteristics of a voice of the individual based on the recorded audio input, wherein the audio input includes a decibel level of the conversation;

instruct, based on the decibel level of the conversation, the audio input device to change from a passive state to an active state;

determine that an amity level of the conversation is greater than a threshold value, wherein

the amity level is one of an acquaintance or a friend, and

the amity level is determined based on:

the instruction to the audio input device to change from the passive state to the active state; and

contextual information associated with specific words or phrases used in the conversation, the voice characteristics of the individual, and at least one of frequency of meetings between the user and the individual, a time since previous meeting between the user and the individual, or a time since first meeting between the user and the individual;

compare, based on the determination that the amity level is greater than the threshold value, the voice characteristics of the voice of the individual to voice characteristics of voice profiles;

as a result of the voice and one of the voice profiles meeting a similarity threshold, determine the name associated with one of the voice profiles; and

providing the name to the user who is having the conversation with the individual.

10. The computer system of claim 9 , wherein the program instructions further cause the at least one processor to:

monitor an audio space in proximity to the user; and

detect a presence of speech in the audio input captured in the audio space, wherein the speech is associated with the conversation.

11. The computer system of claim 10 , wherein the program instructions further cause the at least one processor to:

determine whether the conversation includes a named greeting, the named greeting being an utterance from one of the users or the individual including the name of the individual, wherein the voice characteristics are determined as a result of the named greeting being absent in the conversation.

Assignments (1)

Continuity (1)

References Cited (24)