Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Method, apparatus and computer program providing a multi-speaker database for concatenative text-to-speech synthesis

Method, apparatus and computer program providing a multi-speaker database for concatenative text-to-speech synthesis

US Patent 7716052 · Granted May 11, 2010

Estimated economic value: $10,477,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Natural language selection of objects in image data2025
Shared encoder for natural language understanding processing2025
Speech processing2024
Natural language selection of objects in image data2024
Multilingual intent recognition2024
Model configuration2024
Speech processing2023
Leveraging unpaired text data for training end-to-end spoken language understand2023
Using closed captions as parallel training data for customization of closed capt2022
Learning transcription errors in speech recognition tasks2021
Detecting and recovering out-of-vocabulary words in voice-to-text transcription 2021
Soft-forgetting for connectionist temporal classification based automatic speech2021