公开(公告)号：US20200035215A1

公开(公告)日：2020-01-30

申请号：US16593161

申请日：2019-10-04

Applicant: LG Electronics Inc.

Inventor： Siyoung YANG ,  Minook KIM ,  Sangki KIM ,  Yongchul PARK ,  Juyeong JANG ,  Sungmin HAN

IPC: G10L13/02 ,  G10L25/63 ,  G10L25/30 ,  G10L15/30 ,  G06F17/16

Abstract: A speech synthesis method and apparatus based on emotion information are disclosed. A speech synthesis method based on emotion information extracts speech synthesis target text from received data and determines whether the received data includes situation explanation information. First metadata corresponding to first emotion information is generated on the basis of the situation explanation information. When the extracted data does not include situation explanation information, second metadata corresponding to second emotion information generated on the basis of semantic analysis and context analysis is generated. One of the first metadata and the second metadata is added to the speech synthesis target text to synthesize speech corresponding to the extracted data. A speech synthesis apparatus of this disclosure may be associated with an artificial intelligence module, drone (unmanned aerial vehicle, UAV), robot, augmented reality (AR) devices, virtual reality (VR) devices, devices related to 5G services, and the like.

公开(公告)号：US20200005763A1

公开(公告)日：2020-01-02

申请号：US16561410

申请日：2019-09-05

Applicant: LG ELECTRONICS INC.

Inventor： Jonghoon CHAE ,  Minook KIM ,  Sangki KIM ,  Yongchul PARK ,  Siyoung YANG ,  Juyeong JANG ,  Sungmin HAN

IPC: G10L13/08 ,  G10L15/02 ,  G10L13/047 ,  G10L13/033

Abstract: Disclosed is an artificial intelligence (AI)-based voice sampling apparatus for providing a speech style, including a rhyme encoder configured to receive a user's voice, extract a voice sample, and analyze a vocal feature included in the voice sample, a text encoder configured to receive text for reflecting the vocal feature, a processor configured to classify the vocal feature of the voice sample input to the rhyme encoder according to a label, extract an embedding vector representing the vocal feature from the label, and generate a speech style from the embedding vector and apply the generated speech style to the text, and a rhyme decoder configured to output synthesized voice data in which the speech style is applied to the text by the processor.