Voice interpretation device
AssigneeLG Electronics Inc.
InventorsJonghoon Chae, Juyeong Jang, Yongchul Park, Siyoung Yang, Sungmin Han
Life of this patent
Estimating the term…
Abstract
An apparatus that includes a microphone and a processor. The processor is configured to receive, via the microphone, audio comprising voice of a person, and determine whether the received audio is an actual voice or a synthesized voice. The apparatus also provides a first notification indicating that the received audio is the actual voice when the received audio is the actual voice, and provides a second notification indicating that the received audio is the synthesized voice when the received audio is the synthesized voice.
Claims13
An apparatus, comprising:
- a microphone;
- and
- a processor configured to:
- receive, via the microphone, audio comprising voice;
- extract a first power spectrum corresponding to a first voice unit of the received audio;
- extract a second power spectrum corresponding to a second voice unit of the received audio;
- obtain similarity between the first power spectrum and the second power spectrum based on a comparison of the first power spectrum with the second power spectrum;
- determine that the received audio is a synthesized voice if the obtained similarity is less than a reference value;
- and
- output a first notification indicating that the received audio is the synthesized voice when the received audio is determined to be the synthesized voice.
A method performed at a device having a microphone, the method comprising:
- receiving, via the microphone, audio comprising voice;
- extracting a first power spectrum corresponding to a first voice unit of the received audio;
- extracting a second power spectrum corresponding to a second voice unit of the received audio;
- obtaining similarity between the first power spectrum and the second power spectrum based on a comparison of the first power spectrum with the second power spectrum;
- determining that the received audio is a synthesized voice if the obtained similarity is less than a reference value;
- and
- outputting a first notification indicating that the received audio is the synthesized voice when the received audio is determined to be the synthesized voice.
Dependencies are inferred from the claim text.