# US 2025/0166602 A1 · Systems and methods for speech generation by emotional voice conversion

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2025/0166602 A1
- Document ID: US20250166602A1
- Status: Published application
- Kind: A1
- Application number: 18/953,970
- Filed: 2024-11-20
- Published: 2025-05-22
- Earliest claimed: 2023-11-22
- Assignees: Datum Point Labs Inc.
- Applicants: Datum Point Labs Inc.
- Inventors: Kyungseok Oh; Hanseok Ko; Bonhwa Ku
- Web page: https://patentgrep.com/patent/US20250166602A1

## CPC

- G10L 13/027: Concept to speech synthesisers; Generation of natural phrases from machine-based concepts (generation of parameters for speech synthesis out of text G10L13/08)
- G10L 13/033: Voice editing, e.g. manipulating the voice of the synthesiser
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

Embodiments described herein include voice conversion (VC) based Emotion Data generation. Embodiments described herein may generate a multi-speaker multi-emotion dataset by changing the gender style of the input speech while retaining its emotion style and linguistic contents. For example, a single-speaker multi-emotion dataset may be used as the input speech and a multi-speaker single emotion dataset may be the target speech. The generated data may be used as the training data for a text to speech (TTS) model so that it can generate speeches with diverse styles of emotions and speakers. To generate a multi-speaker multi-emotion dataset, embodiments herein add an emotion encoder to a VC model and use acoustic properties to preserve the emotion speech style of the input speech while changing just the gender style to the target gender style.

## Claims

### Claim 1

A method of speech generation, comprising:
generating, via an emotion encoder, an emotion feature based on an input audio including a first utterance;
generating, via a style encoder, and encoded style based on a reference audio including a second utterance;
generating, via a decoder, a converted audio utterance based on the emotion feature and the encoded style;
computing a loss function based on at least one of:
acoustic feature matching of the input audio to the converted audio utterance; or
a source dataset classification from a source dataset classifier; and
training at least one of the emotion encoder or the style encoder based on the loss function.
