System and method for creating timbres
WC Huffman, M Pappas - US Patent 11,017,788, 2021 - Google Patents
A method of building a new voice having a new timbre using a timbre vector space includes
receiving timbre data filtered using a temporal receptive field. The timbre data is mapped in …
receiving timbre data filtered using a temporal receptive field. The timbre data is mapped in …
System and method for creating timbres
WC Huffman, M Pappas - US Patent 11,854,563, 2023 - Google Patents
A method of building a new voice having a new timbre using a timbre vector space includes
receiving timbre data filtered using a temporal receptive field. The timbre data is mapped in …
receiving timbre data filtered using a temporal receptive field. The timbre data is mapped in …
Multi-stage adaptive system for content moderation
WC Huffman, M Pappas, H Howie - US Patent 11,996,117, 2024 - Google Patents
A toxicity moderation system has an input configured to receive speech from a speaker. The
system includes a multi-stage toxicity machine learning system having a first stage and a …
system includes a multi-stage toxicity machine learning system having a first stage and a …
Streaming voice conversion method and apparatus and computer readable storage medium using the same
XIE Jiebin, R Wang, D Huang, Z Tang, Y Liu… - US Patent …, 2022 - Google Patents
The present disclosure provides a streaming voice conversion method as well as an
apparatus and a computer readable storage medium using the same. The method includes …
apparatus and a computer readable storage medium using the same. The method includes …
Method and apparatus for voice conversion and storage medium
R Wang, Z Tang, D Huang, XIE Jiebin, Z Zhao… - US Patent …, 2024 - Google Patents
The present disclosure discloses a voice conversion method. The method includes:
obtaining a to-be-converted voice, and extracting acoustic features of the to-be-converted …
obtaining a to-be-converted voice, and extracting acoustic features of the to-be-converted …