Invention Grant
- Patent Title: Using speech to text data in training text to speech models
-
Application No.: US17245048Application Date: 2021-04-30
-
Publication No.: US11699430B2Publication Date: 2023-07-11
- Inventor: Andrew R. Freed , Vamshi Krishna Thotempudi , Sujatha B. Perepa
- Applicant: International Business Machines Corporation
- Applicant Address: US NY Armonk
- Assignee: International Business Machines Corporation
- Current Assignee: International Business Machines Corporation
- Current Assignee Address: US NY Armonk
- Agent David K. Mattheis
- Main IPC: G10L13/08
- IPC: G10L13/08 ; G10L13/06 ; G06N20/00
Abstract:
A system and method for providing a text to speech output by receiving user audio data, determining a user region-specific-pronunciation classification according to the audio data, determining text for a response to the user according to the audio data, identifying a portion from the text, where a region specific-pronunciation dictionary includes the portion, and using a phoneme string, from the dictionary selected according to the user region-specific pronunciation classification, for the word in a text to speech output to the user.
Public/Granted literature
- US20220351715A1 USING SPEECH TO TEXT DATA IN TRAINING TEXT TO SPEECH MODELS Public/Granted day:2022-11-03
Information query
