IP Library › Granted Patent US 12,744,030
Granted Patent B2
US 12,744,030 · App. 18/675,792 · Granted Sep 22, 2026

Method and system for a parametric speech synthesis

Inventors: Joe Garman (Washington, DC); Ophir Frieder (Chevy Chase, MD)
Assignee: Georgetown University
G10L13/10G06F40/263G06N3/08G10L13/047G10L13/086
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,744,030
App. No.
18/675,792
Granted
Sep 22, 2026
Kind
B2
Abstract

Embodiments of the present systems and methods may provide techniques for synthesizing speech in any voice in any language in any accent. For example, in an embodiment, a text-to-speech conversion system may comprise a text converter adapted to convert input text to at least one phoneme selected from a plurality of phonemes stored in memory, a machine-learning model storing voice patterns for a plurality of individuals and adapted to receive the at least one phoneme and an identity of a speaker and to generate acoustic features for each phoneme, and a decoder adapted to receive the generated acoustic features and to generate a speech signal simulating a voice of the identified speaker in a language.

Claims (29)

1 . A speech conversion system comprising;

a memory for storing a plurality of phonemes;

a text converter adapted to convert input text to at least one phoneme selected from the plurality of phonemes stored in the memory, wherein the text converter is further adapted to detect a language of the input text;

a machine-learning model storing voice patterns for a plurality of individuals and adapted to receive the at least one phoneme from the text converter and an identity of a speaker and to generate and enhance acoustic features for each of the at least one phoneme, wherein the machine-learning model comprises a deep learning neural network that uses (i) phoneme embedding, (ii) speaker embedding, and (iii) language embedding, and wherein the voice patterns comprise a plurality of production components and a plurality of acoustic components arranged in a matrix, each of the plurality of production components contributing a selected amount to each of the acoustic components, such that the selected amount contributed is present in the matrix for each pair of production component and acoustic component, and wherein the enhanced acoustic features comprise at least one of spectral enhancement or focal enhancement; and

a decoder adapted to receive the generated acoustic features from the machine-learning model and to generate a speech signal simulating a voice of the identified speaker in the language, wherein the generated acoustic features include accent acoustic features such that the generated speech signal further simulates the voice of the identified speaker in the language and in an accent.

2 . The system of claim 1 , wherein the at least one phenome comprises a phoneme of the International Phonetic Alphabet and silence and breath.

3 . The system of claim 1 , wherein the machine-learning model comprises a neural network model.

4 . The system of claim 1 , wherein spectral enhancement comprises increasing a peak of a spectral envelope or decreasing a trough of the spectral envelope and focal enhancement comprises emphasizing the difference between a first frame and a second frame.

5 . The system of claim 1 , wherein the generated acoustic features include accent acoustic features and the generated speech signal further simulates a voice of the identified speaker in a language and in an accent.

6 . The system of claim 5 , wherein the accent corresponds to a native accent of the identified speaker.

7 . The system of claim 1 , wherein the plurality of production components comprise phones, coarticulation, prosody from linguistic features, and prosody from extra-linguistic features, and the plurality of acoustic components comprise spectrum, power, duration, and pitch.

8 . A speech conversion method implemented in a computer system comprising a processor, memory accessible by the processor, and computer program instructions stored in the memory and executable by the processor, the method comprising:

storing a plurality of phonemes in the memory;

converting input text to at least one phoneme selected from the plurality of phonemes stored in the memory;

detecting a language of the input text;

storing, in a machine-learning model at the computer system, voice patterns for a plurality of individuals, receiving, at the machine-learning model at the computer system, the at least one phoneme and an identity of a speaker, and generating and enhancing, with the machine-learning model at the computer system, acoustic features for each of the at least one phoneme, wherein the machine-learning model comprises a deep learning neural network that uses (i) phoneme embedding, (ii) speaker embedding, and (iii) language embedding, and wherein the voice patterns comprise a plurality of production components and a plurality of acoustic components arranged in a matrix, each of the plurality of production components contributing a selected amount to each of the acoustic components, such that the selected amount contributed is present in the matrix for each pair of production component and acoustic component, and wherein enhancing acoustic features comprises at least one of spectral enhancement or focal enhancement; and

receiving, at the computer system, the generated acoustic features from the machine learning model, and generating, at the computer system, a speech signal simulating a voice of the identified speaker in the language, wherein the generated acoustic features include accent acoustic features such that the generated speech signal further simulates the voice of the identified speaker in the language and in an accent.

9 . The method of claim 8 , wherein the at least one phenome comprises a phoneme of the International Phonetic Alphabet and silence and breath.

10 . The method of claim 8 , wherein the machine-learning model comprises a neural network model.

11 . The method of claim 8 , wherein spectral enhancement comprises increasing a peak of a spectral envelope or decreasing a trough of the spectral envelope and focal enhancement comprises emphasizing the difference between a first frame and a second frame.

12 . The method of claim 8 , wherein the generated acoustic features include accent acoustic features and the generated speech signal further simulates a voice of the identified speaker in a language and in an accent.

13 . The method of claim 12 , wherein the accent corresponds to a native accent of the identified speaker.

14 . The method of claim 8 , wherein the plurality of production components comprise phones, coarticulation, prosody from linguistic features, and prosody from extra-linguistic features, and the plurality of acoustic components comprise spectrum, power, duration, and pitch.

15 . A speech conversion system comprising;

a memory for storing a plurality of phonemes;

a text converter adapted to convert input text to at least one phoneme selected from the plurality of phonemes stored in the memory, wherein the text converter is further adapted to detect a language of the input text;

a machine-learning model storing voice patterns for a plurality of individuals and adapted to receive the at least one phoneme from the text converter and an identity of a speaker and to generate and enhance acoustic features for each of the at least one phoneme, wherein the machine-learning model comprises a deep learning neural network that uses (i) phoneme embedding, (ii) speaker embedding, and (iii) language embedding,

wherein the voice patterns comprise a plurality of production components and a plurality of acoustic components arranged in a matrix, each of the plurality of production components contributing a selected amount to each of the acoustic components, such that the selected amount contributed is present in the matrix for each pair of production component and acoustic component, and having voice pattern options, and wherein the enhanced acoustic features comprise at least one of spectral enhancement or focal enhancement; and

a decoder adapted to receive the generated acoustic features from the machine-learning model and to generate a speech signal simulating a voice of the identified speaker in the language, wherein the generated acoustic features include accent acoustic features such that the generated speech signal further simulates the voice of the identified speaker in the language and in an accent.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 4, 2024
From: GARMAN, JOE; FRIEDER, OPHIR
To: GEORGETOWN UNIVERSITY
Reel/Frame 067613/0463 →
Continuity (5)
Continuation 18164782 · Feb 6, 2023
Continuation 17252766 · Jun 14, 2019
Provisional Application 62822258 · Mar 22, 2019
Provisional Application 62686838 · Jun 19, 2018
Related Publication 20240428778A1 · Dec 26, 2024
References Cited (33)
US 6463412B1 · Baumgartner · 2002 [cited by examiner]
US 9484014B1 · Kaszczuk · 2016 [cited by applicant]
US 9865253B1 · De Leon · 2018 [cited by examiner]
US 9978359B1 · Kaszczuk · 2018 [cited by applicant]
US 10796686B2 · Arik · 2020 [cited by examiner]
US 11605371B2 · Garman · 2023 [cited by applicant]
US 12020687B2 · Garman · 2024 [cited by examiner]
US 20030163316A1 · Addison et al. · 2003 [cited by applicant]
US 20040225501A1 · Cutaia · 2004 [cited by applicant]
US 20070168189A1 · Tamura · 2007 [cited by applicant]
US 20080065381A1 · Matsumoto · 2008 [cited by applicant]
US 20080126093A1 · Sivadas · 2008 [cited by applicant]
US 20080201150A1 · Tamura · 2008 [cited by applicant]
US 20090281807A1 · Hirose · 2009 [cited by applicant]
US 20100082329A1 · Silverman · 2010 [cited by examiner]
US 20120265533A1 · Honeycutt · 2012 [cited by applicant]
US 20130151256A1 · Nakano · 2013 [cited by examiner]
US 20130226583A1 · Kadirkamanathan et al. · 2013 [cited by applicant]
US 20150364128A1 · Satoyama et al. · 2015 [cited by applicant]
US 20160372116A1 · Summerfield · 2016 [cited by examiner]
US 20170309272A1 · Vanreusel · 2017 [cited by applicant]
US 20180190269A1 · Lokeswarappa · 2018 [cited by applicant]
US 20180254034A1 · Li · 2018 [cited by applicant]
US 20180336880A1 · Arik · 2018 [cited by applicant]
US 20210256961A1 · Garman · 2021 [cited by examiner]
US 20240420681A1 · Gupta · 2024 [cited by examiner]
CN 107301859 · 2017 [cited by applicant]
EP 1612695 · 2006 [cited by applicant]
JP 2006243178 · 2006 [cited by applicant]
JP 2010286608A · 2010 [cited by examiner]
JP 2011028131 · 2011 [cited by applicant]
KR 101787497B1 · 2017 [cited by examiner]
Jia Y, Zhang Y, Weiss R, Wang Q, Shen J, Ren F, Nguyen P, Pang R, Lopez Moreno I, Wu Y. Transfer learning from speaker verification to multispeaker text-to-speech synthesis. Advances in neural information processing sys… [cited by examiner]