NvidiaGranted patentAudio & voiceInterest 6/10

Nvidia patents method to create new synthetic voices by mixing voice traits

Nvidia describes a system that creates new, artificial voices by blending the unique characteristics of existing speakers. It works by taking data that defines a voice's tone and pitch, mixing these traits to form a new voice profile, and then using that profile to read out text as audio.

Why it mattersThis technology could allow developers to create diverse, non-human voices for virtual assistants or interactive characters without needing to record real people.

In the filing’s own words

In various examples, generating synthetic voices for speech for conversational systems and applications is described herein. Systems and methods described herein may generate data, such as data representing speaker embeddings (e.g., timbre, etc.) and/or frequency values (e.g., pitch, etc.), which is then used to generate audio data representing speech in synthetically produced voices. For instance, speaker embeddings may be used to generate a new speaker embedding associated with a synthetically produced voice, such as by linearly interpolating between the speaker embeddings and/or sampling an embedding space associated with speaker embeddings. Additionally, a frequency value associated with the synthetically produced voice may be identified, such as by randomly sampling from a distribution of frequency values. A component may then use the speaker embedding, the frequency value, and/or input data representing linguistic content to generate audio data representing the speech in the synthetically produced voice.

What exactly they claim (claim 1)

1. A system comprising: one or more processors to: obtain one or more first speaker embeddings corresponding to one or more speaker voices; determine, based at least on the one or more first speaker embeddings, one or more second speaker embeddings corresponding to one or more synthetic voices; determine, based at least on sampling a distribution of frequency values associated with voices, one or more frequency values corresponding to the one or more synthetic voices; and generate, using the one or more second speaker embeddings and the one or more frequency values, and based at least on input data representative of linguistic content, synthetic audio data representative of speech corresponding to the linguistic content.

Facts

Company
Nvidia (NVIDIA Corporation)
Official title
Generating synthetic voices
Patent number
US12793697B2
Application number
18631614
Filed
Apr 10, 2024
Granted
Nov 10, 2026
Inventors
2
Claims
20

Classified under

G10L 13/0335 Physics & computing

More from Nvidia in Audio & voice

Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.