Supervised speech separation based on deep learning: An overview
Speech separation is the task of separating target speech from background interference.
Traditionally, speech separation is studied as a signal processing problem. A more recent …
Traditionally, speech separation is studied as a signal processing problem. A more recent …
Time-frequency masking for speech separation and its potential for hearing aid design
DL Wang - Trends in amplification, 2008 - journals.sagepub.com
A new approach to the separation of speech from speech-in-noise mixtures is the use of time-
frequency (TF) masking. Originated in the field of computational auditory scene analysis, TF …
frequency (TF) masking. Originated in the field of computational auditory scene analysis, TF …
Intelligent device arbitration and control
KW Piersol, RM Orr, DJ Mandel - US Patent 10,089,072, 2018 - Google Patents
This relates to systems and processes for using a virtual assistant to arbitrate among and/or
control electronic devices. In one example process, a first electronic device samples an …
control electronic devices. In one example process, a first electronic device samples an …
Intelligent automated assistant for TV user interactions
M Van Os, HJ Saddler, LT Napolitano… - US Patent …, 2016 - Google Patents
2015-03-25 Assigned to APPLE INC. reassignment APPLE INC. ASSIGNMENT OF
ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: NAPOLITANO, LIA …
ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: NAPOLITANO, LIA …
Digital assistant providing whispered speech
TJ Raitio, MJ Hunt, HB Richards… - US Patent …, 2019 - Google Patents
2016-10-25 Assigned to APPLE INC. reassignment APPLE INC. ASSIGNMENT OF
ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: HUNT, MELVYN J …
ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: HUNT, MELVYN J …
Intelligent automated assistant in a messaging environment
H04L51/02—User-to-user messaging in packet-switching networks, transmitted according to
store-and-forward or real-time protocols, eg e-mail using automatic reactions or user …
store-and-forward or real-time protocols, eg e-mail using automatic reactions or user …
Multi-command single utterance input method
TR Gruber, HJ Saddler, JR Bellegarda… - US Patent …, 2018 - Google Patents
Abstract Systems and processes are disclosed for handling a multi-part voice command for a
virtual assistant. Speech input can be received from a user that includes multiple actionable …
virtual assistant. Speech input can be received from a user that includes multiple actionable …
Competing devices responding to voice triggers
BJ Newendorp, ES DiBiase - US Patent 9,721,566, 2017 - Google Patents
G06F3/00—Input arrangements for transferring data to be processed into a form capable of
being handled by the computer; Output arrangements for transferring data from processing …
being handled by the computer; Output arrangements for transferring data from processing …
Voice trigger for a digital assistant
J Binder, SD Post, O Tackin, TR Gruber - US Patent 10,199,051, 2019 - Google Patents
G10L21/00—Processing of the speech or voice signal to produce another audible or non-
audible signal, eg visual or tactile, in order to modify its quality or its intelligibility
audible signal, eg visual or tactile, in order to modify its quality or its intelligibility
Speaker identification and unsupervised speaker adaptation techniques
Y Kim, SS Kajarekar - US Patent 10,127,911, 2018 - Google Patents
Abstract Systems and processes for generating a speaker profile for use in performing
speaker identification for a virtual assistant are provided. One example process can include …
speaker identification for a virtual assistant are provided. One example process can include …