Apparatus for media entity pronunciation using deep learning
D Bromand - US Patent 11,501,764, 2022 - Google Patents
Methods, systems, and related products for voice-enabled computer systems are described.
A machine learning model is trained to produce pronunciation output based on text input …
A machine learning model is trained to produce pronunciation output based on text input …
Audio information processing method, audio information processing apparatus, electronic device, and storage medium
S Zhang, M Lei - US Patent 12,154,545, 2024 - freepatentsonline.com
In various embodiments, this application provides an audio information processing method,
an audio information processing apparatus, an electronic device, and a storage medium. An …
an audio information processing apparatus, an electronic device, and a storage medium. An …
Automated domain-specific constrained decoding from speech inputs to structured resources
Methods, systems, and computer program products for automated domain-specific
constrained decoding from speech inputs to structured resources are provided herein. A …
constrained decoding from speech inputs to structured resources are provided herein. A …
Method for training speech recognition model, method and system for speech recognition
2022-06-09 Assigned to INSTITUTE OF AUTOMATION, CHINESE ACADEMY OF
SCIENCES reassignment INSTITUTE OF AUTOMATION, CHINESE ACADEMY OF …
SCIENCES reassignment INSTITUTE OF AUTOMATION, CHINESE ACADEMY OF …
Method and device for compressing finite-state transducers data
Z Liang - US Patent App. 17/782,152, 2023 - Google Patents
(57) ABSTRACT A method and device for compressing FST data are pro vided. The method
includes: acquiring to-be-compressed FST data, where the FST data includes state transition …
includes: acquiring to-be-compressed FST data, where the FST data includes state transition …
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 …
Alphanumeric sequence biasing for automatic speech recognition using a grammar and a speller finite state transducer
B Haynor, P Aleksic - US Patent 11,942,091, 2024 - Google Patents
Speech processing techniques are disclosed that enable determining a text representation
of alphanumeric sequences in captured audio data. Various implementations include …
of alphanumeric sequences in captured audio data. Various implementations include …
Contextualized streaming end-to-end speech recognition with trie-based deep biasing and shallow fusion
In one embodiment, a method includes receiving a user's utterance comprising a word in a
custom vocabulary list of the user, generating a previous token to represent a previous audio …
custom vocabulary list of the user, generating a previous token to represent a previous audio …