# US 2025/0166601 A1 · Systems and methods for adaptive text to speech for diverse styles

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

- Number: US 2025/0166601 A1
- Document ID: US20250166601A1
- Status: Published application
- Kind: A1
- Application number: 18/952,738
- Filed: 2024-11-19
- Published: 2025-05-22
- Earliest claimed: 2023-11-22
- Assignees: Datum Point Labs Inc.
- Applicants: Datum Point Labs Inc.
- Inventors: Jeongki Min; Hanseok Ko; Bonhwa Ku
- Web page: https://patentgrep.com/patent/US20250166601A1

## 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
- G06N 3/08: Learning methods
- G06N 3/045: Combinations of networks
- G10L 13/047: Architecture of speech synthesisers
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Embodiments described herein provide adaptive text to speech (TTS) methods for generating voices in diverse styles is built on a pretrained TTS model and an age/gender/emotion recognition model and conditional LoRa (Low-Rank Adaptation of Large Language Models) module that is a style adaptation module. The style adaptation module generates style vectors, where a style consists of a combination of acoustic properties such as tone, speaking rate, accent, etc. These methods allow for generation of diverse voice styles, including seen and unseen styles (i.e., styles not used in the training dataset).

## Claims

### Claim 1

A method of speech generation, comprising:
generating a style vector via a style module based on an input speech signal;
generating an encoded text via an encoder based on an input text;
modifying the encoded text by a plurality of neural network based layers conditioned by the style vector; and
decoding the modified encoded text to provide an output speech audio.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
summing the encoded text with a speaker ID,
wherein the modifying the encoded text is performed using the summed encoded text.

### Claim 3 (depends on 1)

The method of claim 1, wherein the plurality of neural network based layers includes at least one of a conditional Low-Rank Adaptation module, or a variance adaptor.

### Claim 4 (depends on 1)

The method of claim 1, further comprising playing the output speech audio via a speaker.

### Claim 5 (depends on 1)

A smartphone configured to perform the method of claim 1.