Speech generation using crosslingual phoneme map**
A Patel, S Tazari - US Patent 12,080,271, 2024 - Google Patents
Computer generated speech can be generated for cross-lingual natural language textual
data streams by utilizing a universal phoneme set. In a variety of implementations, the …
data streams by utilizing a universal phoneme set. In a variety of implementations, the …
Systems and methods for generating locale-specific phonetic spelling variations
Abstract Systems and methods for generating phonetic spelling variations of a given word
based on locale-specific pronunciations. A phoneme-letter density model may be configured …
based on locale-specific pronunciations. A phoneme-letter density model may be configured …
Using speech to text data in training text to speech models
AR Freed, VK Thotempudi, SB Perepa - US Patent 11,699,430, 2023 - Google Patents
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 a user region-specific-pronunciation classification according to the audio data …
Phoneme recognizer customizable keyword spotting system with keyword adaptation
A wake-up word for a digital assistant may be specified by a user to trigger the digital
assistant to respond to the wake-up word, with the user providing one or more initial …
assistant to respond to the wake-up word, with the user providing one or more initial …
Method and system for visio-linguistic understanding using contextual language model reasoners
This disclosure relates generally to visio-linguistic understanding. Conventional methods
use contextual visio-linguistic reasoner for visio-linguistic understanding which requires …
use contextual visio-linguistic reasoner for visio-linguistic understanding which requires …