Inventor profile of:

Ye Jia

City:

Mountain View, California

Country:

United States

Published Applications:

16

Last publication date:

2025-03-20

Top Assignees for applications by Ye Jia

The entities that hold a legal rights for patent applications filed by inventor Jia Ye:

Recent patent applications by Jia Ye

Ye Jia from Mountain View, US has applied for patents for these inventions. The list has both pending applications and granted patents:

#1 | 2025-03-20
US20250095630A1
Physics

SYNTHESIS OF SPEECH FROM TEXT IN A VOICE OF A TARGET SPEAKER USING NEURAL NETWORKS

#2 | 2024-12-05
US20240404506A1
Physics

MULTILINGUAL SPEECH SYNTHESIS AND CROSS-LANGUAGE VOICE CLONING

#3 | 2024-10-10
US20240339106A1
Physics

Phonemes And Graphemes for Neural Text-to-Speech

#4 | 2024-08-15
US20240273311A1
Physics

Robust Direct Speech-to-Speech Translation

#5 | 2024-05-16
US20240161730A1
Physics

Parallel Tacotron Non-Autoregressive and Controllable TTS

#6 | 2024-04-04
US20240112667A1
Physics

Synthesis of speech from text in a voice of a target speaker using neural networks

#7 | 2024-02-22
US20240062743A1
Physics

Unsupervised parallel tacotron non-autoregressive and controllable text-to-speech

#8 | 2023-06-08
US20230178068A1
Physics

Multilingual speech synthesis and cross-language voice cloning

#9 | 2023-03-02
US20230064749A1
Physics

Two-Level Speech Prosody Transfer

#10 | 2023-01-19
US20230013777A1
Physics

Robust direct speech-to-speech translation

#11 | 2022-11-03
US20220351713A1
Physics

Synthesis of speech from text in a voice of a target speaker using neural networks

#12 | 2022-09-29
US20220310059A1
Physics

Phonemes and graphemes for neural text-to-speech

#13 | 2022-09-22
US20220301543A1
Physics

Unsupervised parallel tacotron non-autoregressive and controllable text-to-speech

#14 | 2022-04-21
US20220122582A1
Physics

Parallel tacotron non-autoregressive and controllable TTS

#15 | 2022-02-17
US20220051654A1
Physics

Two-level speech prosody transfer

#16 | 2021-07-08
US20210209315A1
Physics

Direct speech-to-speech translation via machine learning

InventorID:

5131429 ⎘