公开(公告)号：US20240428018A1

公开(公告)日：2024-12-26

申请号：US18827103

申请日：2024-09-06

Applicant: Warner Bros. Entertainment Inc.

Inventor： Aansh Malik ,  Ha Thanh Nguyen

IPC: G06F40/47 ,  G06F40/58 ,  G10L15/00 ,  G10L15/16

Abstract: A method and system for automated voice casting compares candidate voices samples from candidate speakers in a target language with a primary voice sample from a primary speaker in a primary language. Utterances in the audio samples of the candidates speakers and the primary speaker are identified and typed and voice samples generated that meet applicable utterance type criteria. A neural network is used to generate an embedding for the voice samples. A voice sample can include groups of different utterance types and embeddings generated for each utterance group in the voice sample and then combined in a weighted form wherein the resulting embedding emphasizes selected utterance types. Similarities between embeddings for the candidate voice samples relative to the primary voice sample are evaluated and used to select a candidate speaker that is a vocal match.

公开(公告)号：US12086558B2

公开(公告)日：2024-09-10

申请号：US17196285

申请日：2021-03-09

Applicant: Warner Bros. Entertainment Inc.

Inventor： Aansh Malik ,  Ha Thanh Nguyen

IPC: G06F40/47 ,  G06F40/58 ,  G10L15/00 ,  G10L15/16

CPC classification number: G06F40/47 ,  G06F40/58 ,  G10L15/005 ,  G10L15/16

Abstract: A method and system for automated voice casting compares candidate voices samples from candidate speakers in a target language with a primary voice sample from a primary speaker in a primary language. Utterances in the audio samples of the candidates speakers and the primary speaker are identified and typed and voice samples generated that meet applicable utterance type criteria. A neural network is used to generate an embedding for the voice samples. A voice sample can include groups of different utterance types and embeddings generated for each utterance group in the voice sample and then combined in a weighted form wherein the resulting embedding emphasizes selected utterance types. Similarities between embeddings for the candidate voice samples relative to the primary voice sample are evaluated and used to select a candidate speaker that is a vocal match.

公开(公告)号：US20210279427A1

公开(公告)日：2021-09-09

申请号：US17196285

申请日：2021-03-09

Applicant: Warner Bros. Entertainment Inc.

Inventor： Aansh Malik ,  Ha Thanh Nguyen

IPC: G06F40/47 ,  G06F40/58 ,  G10L15/16 ,  G10L15/00

Abstract: A method and system for automated voice casting compares candidate voices samples from candidate speakers in a target language with a primary voice sample from a primary speaker in a primary language. Utterances in the audio samples of the candidates speakers and the primary speaker are identified and typed and voice samples generated that meet applicable utterance type criteria. A neural network is used to generate an embedding for the voice samples. A voice sample can include groups of different utterance types and embeddings generated for each utterance group in the voice sample and then combined in a weighted form wherein the resulting embedding emphasizes selected utterance types. Similarities between embeddings for the candidate voice samples relative to the primary voice sample are evaluated and used to select a candidate speaker that is a vocal match.