17975074. METHOD FOR PROCESSING VOICE SIGNALS OF MULTIPLE SPEAKERS, AND ELECTRONIC DEVICE ACCORDING THERETO simplified abstract (Samsung Electronics Co., Ltd.)

METHOD FOR PROCESSING VOICE SIGNALS OF MULTIPLE SPEAKERS, AND ELECTRONIC DEVICE ACCORDING THERETO

Organization Name

Samsung Electronics Co., Ltd.

Inventor(s)

Young Ho Han of Suwon-si (KR)

Nam Hoon Kim of Suwon-si (KR)

Jae Young Roh of Suwon-si (KR)

Chi Youn Park of Suwon-si (KR)

Kyung Min Lee of Suwon-si (KR)

Keun Seok Cho of Suwon-si (KR)

Jong Youb Ryu of Suwon-si (KR)

METHOD FOR PROCESSING VOICE SIGNALS OF MULTIPLE SPEAKERS, AND ELECTRONIC DEVICE ACCORDING THERETO - A simplified explanation of the abstract

This abstract first appeared for US patent application 17975074 titled 'METHOD FOR PROCESSING VOICE SIGNALS OF MULTIPLE SPEAKERS, AND ELECTRONIC DEVICE ACCORDING THERETO

Simplified Explanation

The patent application describes an electronic device that can analyze speech signals from multiple speakers and determine the relationships between their speech content. Based on this analysis, the device can determine the appropriate response method and perform operations accordingly.

• The electronic device includes a processor and memory to execute instructions.
• It controls a receiver to receive speech signals.
• It can detect feature information from the speech signals of each speaker.
• It determines the relations between the speech content of different speakers.
• It determines a response method based on the determined relations.
• It controls the electronic device to perform operations according to the determined response method.

Potential Applications

• Speech recognition systems: The technology can be used in speech recognition systems to accurately identify and differentiate between multiple speakers.
• Virtual assistants: Virtual assistants can utilize this technology to understand and respond to multiple users in a more personalized and context-aware manner.
• Call centers: Call centers can benefit from this technology by automatically analyzing and categorizing customer calls based on the speakers, allowing for more efficient handling of customer queries.

Problems Solved

• Speaker identification: The technology solves the problem of accurately identifying and distinguishing between multiple speakers in a speech signal.
• Context-aware responses: By determining the relationships between the speech content of different speakers, the technology enables the device to provide more context-aware and personalized responses.
• Efficient operations: The technology allows for the automation of operations based on the determined response method, improving the efficiency of the electronic device.

Benefits

• Enhanced user experience: The technology enables a more personalized and tailored user experience by understanding and responding to multiple speakers.
• Improved efficiency: By automating operations based on the determined response method, the technology improves the efficiency of the electronic device.
• Context-awareness: The ability to determine relationships between speech content allows for more context-aware responses, enhancing the overall functionality of the device.

Original Abstract Submitted

Disclosed is an electronic device. The electronic device includes a processor configured to execute one or more instructions stored in a memory to: control a receiver to receive a speech signal; determine whether the received speech signal includes speech signals of a plurality of different speakers; when the received speech signal includes the speech signals of the plurality of different speakers, detect feature information from a speech signal of each speaker; determine relations between pieces of speech content of the plurality of different speakers, based on the detected feature information; determine a response method based on the determined relations between the pieces of speech content; and control the electronic device such that an operation of the electronic device is performed according to the determined response method.