Granted Patent B1

US 12,562,148 · App. 18/128,766 · Granted Feb 24, 2026

Inventors: Duo Wang (Cambridge, GB); Vincent Laurent J. Pollet (Astene, BE); Mikolaj Wojciech Babianski (Gdansk, PL); Jakub Bartlomiej Swiatkowski (Warsaw, PL)

Assignee: Amazon Technologies, Inc.

G10L13/086G10L15/005G10L15/26

Abstract

Claims (137)

1 . A computer-implemented method comprising:

receiving first multimedia content including video data and first audio data representing first speech spoken by a first speaker in source language;

receiving first speaker embedding data representing first voice identity characteristics of a second speaker different from the first speaker;

processing the first audio data using a first encoder to generate first performance embedding data representing first vocal performance characteristics of the first speech;

receiving first data representing a first transcript to be output as synthesized speech, wherein the first data is in a target language different from the source language;

receiving language embedding data representing language-dependent speech characteristics of the target language;

processing the first data using a second encoder, the first performance embedding data, and the language embedding data to generate first transcript embedding data, the first transcript embedding data corresponding to a first duration;

receiving duration data indicating that the first speech corresponds to a second duration different from the first duration;

generating, using the first transcript embedding data and the duration data, second transcript embedding data corresponding to the second duration;

processing the second transcript embedding data using a first transformation and the first speaker embedding data to generate acoustic embedding data corresponding to the first voice identity characteristics, the first transformation representing an invertible flow;

processing the acoustic embedding data using a decoder and the first speaker embedding data to generate second audio data representing the synthesized speech in the target language, the synthesized speech having the first voice identity characteristics, the first vocal performance characteristics, and the second duration; and

generating, using the video data and the second audio data, second multimedia content representing the video data dubbed with the second audio data.

2 . The computer-implemented method of claim 1 , wherein the first transcript embedding data includes a first transcript embedding corresponding to a first representation of the synthesized speech and a second transcript embedding corresponding to a second representation of the synthesized speech, further comprising:

determining that the first transcript embedding corresponds to a first predicted duration;

determining that the second transcript embedding corresponds to a second predicted duration;

determining, using the duration data, a first modified duration for the first transcript embedding data;

determining, using the duration data, a second modified duration for the second transcript embedding data;

determining that the first modified duration corresponds to a first number of audio frames;

determining that second first modified duration corresponds to a second number of audio frames;

generating a first plurality of transcript embeddings using the first transcript embedding and the first number;

generating a second plurality of transcript embeddings using the second transcript embedding and the second number; and

generating the second transcript embedding data using the first plurality of transcript embeddings and the second plurality of transcript embeddings.

3 . The computer-implemented method of claim 1 , further comprising:

processing the first audio data using a first component to generate third audio data representing the first audio data with at least a portion of noise content removed;

processing the third audio data using the first encoder to generate second performance embedding data;

processing fourth audio data using the first component to generate fifth audio data representing a noise content of the fourth audio data, the fourth audio data representing speech recorded in a low-noise environment;

processing the fifth audio data using a third encoder to generate noise embedding data; and

determining the first performance embedding data using the second performance embedding data and the noise embedding data.

4 . The computer-implemented method of claim 1 , further comprising:

receiving third audio data representing sample speech from a training dataset;

processing the third audio data using a third encoder to generate second speaker embedding data representing voice identity characteristics of a speaker of the sample speech;

processing the third audio data using a fourth encoder and the second speaker embedding data to generate acoustic embedding data representing the sample speech with voice identity characteristics retained;

processing the acoustic embedding data using a second transformation and the second speaker embedding data to generate first data representing the sample speech with voice identity characteristics suppressed;

determining second data representing a second transcript of the sample speech; and

training the second transformation using the first data and the second data to determine a third transformation, wherein the first transformation represents an inverse of the third transformation.

5 . A computer-implemented method comprising:

receiving first multimedia content including video data and first audio data representing first speech in source language;

receiving first data representing first voice identity characteristics for synthesizing second speech;

determining, using the first audio data, second data representing first vocal performance characteristics of the first speech;

receiving third data representing a first transcript of the second speech in a target language;

determining fourth data using the third data and the second data, the fourth data representing the first transcript and corresponding to the first vocal performance characteristics;

generating, using the fourth data, the first data, and a machine learning model, fifth data representing acoustic embeddings for generating the second speech corresponding to the first voice identity characteristics;

determining, using the fifth data, second audio data representing the second speech; and

generating, using the video data and the second audio data, second multimedia content representing the video data dubbed with the second audio data.

6 . The computer-implemented method of claim 5 , wherein the fourth data includes a first transcript embedding corresponding to a first representation of the second speech and a second transcript embedding corresponding to a second representation of the second speech, and the fourth data corresponds to a first duration, the method further comprising:

receiving duration data indicating that the first speech corresponds to a second duration different from the first duration;

determining that the first transcript embedding corresponds to a first predicted duration;

determining that the second transcript embedding corresponds to a second predicted duration;

determining, using the duration data, a first modified duration for the first transcript embedding;

determining, using the duration data, a second modified duration for the second transcript embedding;

determining that the first modified duration corresponds to a first number of audio frames;

determining that second first modified duration corresponds to a second number of audio frames;

generating a first plurality of transcript embeddings using the first transcript embedding and the first number;

generating a second plurality of transcript embeddings using the second transcript embedding and the second number; and

generating the second data using the first plurality of transcript embeddings and the second plurality of transcript embeddings.

7 . The computer-implemented method of claim 5 , further comprising:

processing the first audio data using a first component to generate third audio data representing the first audio data with at least a portion of noise content removed;

determining, using the third audio data, sixth data representing vocal performance characteristics of the first speech;

receiving fourth audio data representing a speech recorded in a low-noise environment;

processing the fourth audio data using the first component to generate fifth audio data representing a noise content of the fourth audio data;

determining, using the fifth audio data, seventh data representing a noise embedding; and

determining the second data using sixth data and the seventh data.

8 . The computer-implemented method of claim 5 , further comprising:

receiving third audio data representing third speech;

determining sixth data representing second voice identity characteristics of the third speech;

determining, using the third audio data and the sixth data, seventh data representing the second speech and the second voice identity characteristics;

processing the seventh data using a first transformation and the sixth data to generate eighth data representing the second speech with the second voice identity characteristics suppressed;

determining ninth data representing a second transcript of the third speech;

training the first transformation using the second data and the ninth data to determine a second transformation; and

determining a third transformation that represents an inverse of the second transformation, the machine learning model corresponding to the third transformation.

9 . The computer-implemented method of claim 5 , further comprising:

receiving first text data representing a second transcript of the first speech;

performing machine translation of the first text data to generate second text data representing a translation of the first speech into the target language; and

processing the second text data to determine the third data.

10 . The computer-implemented method of claim 5 , further comprising:

receiving sixth data representing speech characteristics corresponding to the target language, wherein determining the fourth data includes using the sixth data.

11 . The computer-implemented method of claim 5 , further comprising:

processing the video data to identify facial movement corresponding to the first speech;

determining a first time at which the facial movement begins;

determining a second time at which the facial movement ends; and

determining duration data using the first time and the second time, wherein generating the fifth data is additionally based on the duration data.

12 . The computer-implemented method of claim 5 , further comprising:

determining first timing data representing a first temporal alignment between the first audio data and the video data;

determining, using the first timing data, second timing data representing a second temporal alignment between the second audio data and the video data; and

aligning the video data and the second audio data using the second timing data to generate the second multimedia content.

13 . A system, comprising:

at least one processor; and

at least one memory comprising instructions that, when executed by the at least one processor, cause the system to:

receive first multimedia content including video data and first audio data representing first speech in source language;

determine, using the first audio data, first data representing first voice identity characteristics of a speaker of the first speech;

determine, using the first audio data, second data representing first vocal performance characteristics of the first speech;

receive third data representing a first transcript of second speech to be generated in a target language;

determine fourth data using the third data and the second data, the fourth data representing the first transcript and corresponding to the first vocal performance characteristics;

generate, using the fourth data, the first data, and a machine learning model, fifth data representing acoustic embeddings for generating the second speech corresponding to the first voice identity characteristics;

determine, using the fifth data, second audio data representing the second speech; and

generate, using the video data and the second audio data, second multimedia content representing the video data dubbed with the second audio data.

14 . The system of claim 13 , wherein the fourth data includes a first transcript embedding corresponding to a first representation of the second speech and a second transcript embedding corresponding to a second representation of the second speech, the fourth data corresponds to a first duration, and the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:

receive duration data indicating that the first speech corresponds to a second duration different from the first duration;

determine that the first transcript embedding corresponds to a first predicted duration;

determine that the second transcript embedding corresponds to a second predicted duration;

determine, using the duration data, a first modified duration for the first transcript embedding;

determine, using the duration data, a second modified duration for the second transcript embedding;

determine that the first modified duration corresponds to a first number of audio frames;

determine that second first modified duration corresponds to a second number of audio frames;

generate a first plurality of transcript embeddings using the first transcript embedding and the first number;

generate a second plurality of transcript embeddings using the second transcript embedding and the second number; and

generate the second data using the first plurality of transcript embeddings and the second plurality of transcript embeddings.

15 . The system of claim 13 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:

process the first audio data using a first component to generate third audio data representing the first audio data with at least a portion of noise content removed;

determine, using the third audio data, sixth data representing vocal performance characteristics of the first speech;

receive fourth audio data representing a speech recorded in a low-noise environment;

process the fourth audio data using the first component to generate fifth audio data representing a noise content of the fourth audio data;

determine, using the fifth audio data, seventh data representing a noise embedding; and

determine the second data using sixth data and the seventh data.

16 . The system of claim 13 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:

receive third audio data representing third speech;

determine sixth data representing second voice identity characteristics of the third speech;

determine, using the third audio data and the sixth data, seventh data representing the second speech and the second voice identity characteristics;

process the seventh data using a first transformation and the sixth data to generate second eighth data representing the second speech with the second voice identity characteristics suppressed;

determine ninth data representing a second transcript of the third speech;

train the first transformation using the second data and the ninth data to determine a second transformation; and

determine a third transformation that represents an inverse of the second transformation, the machine learning model corresponding to the third transformation.

17 . The system of claim 13 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:

process the first audio data to determine first text data representing a second transcript of the first speech;

perform machine translation of the first text data to generate second text data representing a translation of the first speech into the target language; and

processing the second text data to determine the third data.

18 . The system of claim 13 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:

receive sixth data representing speech characteristics corresponding to the target language, wherein determining the fourth data includes using the sixth data.

19 . The system of claim 13 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:

process the video data to identify facial movement corresponding to the first speech;

determine a first time at which the facial movement begins;

determine a second time at which the facial movement ends; and

determine duration data using the first time and the second time, wherein generating the fifth data is additionally based on the duration data.

20 . The system of claim 13 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:

determine first timing data representing a first temporal alignment between the first audio data and the video data;

determine, using the first timing data, second timing data representing a second temporal alignment between the second audio data and the video data; and

align the video data and the second audio data using the second timing data to generate the second multimedia content.

Assignments (1)

Continuity (1)

References Cited (42)