Configurable speech recognition system using multiple recognizers
M Newman, A Gillet, DM Krowitz… - US Patent …, 2018 - Google Patents
Techniques for combining the results of multiple recognizers in a distributed speech
recognition architecture. Speech data input to a client device is encoded and processed …
recognition architecture. Speech data input to a client device is encoded and processed …
Audio buffer catch-up apparatus and method with two microphones
R Raghuvir - US Patent 10,121,472, 2018 - Google Patents
A first microphone is operated in a low power sensing mode, and a buffer at the first
microphone is used to temporarily store at least some of the phrase. Subsequently the first …
microphone is used to temporarily store at least some of the phrase. Subsequently the first …
Configurable speech recognition system using a pronunciation alignment between multiple recognizers
M Newman, A Gillet, DM Krowitz… - US Patent …, 2018 - Google Patents
Techniques for combining the results of multiple recognizers in a distributed speech
recognition architecture. Speech data input to a client device is encoded and processed …
recognition architecture. Speech data input to a client device is encoded and processed …
Configurable speech recognition system using multiple recognizers
M Newman, A Gillet, DM Krowitz… - US Patent …, 2014 - Google Patents
Techniques for combining the results of multiple recognizers in a distributed speech
recognition architecture. Speech data input to a client device is encoded and processed …
recognition architecture. Speech data input to a client device is encoded and processed …
Downsampling schemes in a hierarchical neural network structure for phoneme recognition
DAV Cano, G Aradilla, R Gruhn - US Patent 9,595,257, 2017 - Google Patents
Embodiments of the present invention are directed to phoneme recognition. A sequence of
intermediate output posterior vectors is generated from an input sequence of cepstral …
intermediate output posterior vectors is generated from an input sequence of cepstral …
Determining a Product Vector for Performing Dynamic Time Warping
M Gajjar, N Vydyanathan - US Patent App. 14/503,079, 2015 - Google Patents
(57) ABSTRACT A method and a system for determining a product vector for computation of
a Euclidean distance for performing Dynamic Time Warping of a test signal and a template …
a Euclidean distance for performing Dynamic Time Warping of a test signal and a template …
Methods and apparatus for hybrid speech recognition processing
D Willett, J Pinto, WF Ganong III - US Patent 10,971,157, 2021 - Google Patents
Methods and apparatus for selectively performing speech processing in a hybrid speech
processing system. The hybrid speech processing system includes at least one mobile …
processing system. The hybrid speech processing system includes at least one mobile …
Configurable speech recognition system using multiple recognizers
M Newman, A Gillet, DM Krowitz… - US Patent …, 2015 - Google Patents
BACKGROUND In recent years, the availability of voice interfaces for elec tronic devices
using automated speech recognition (ASR) has become more common. Voice interfaces …
using automated speech recognition (ASR) has become more common. Voice interfaces …
Hybrid controller for ASR
D Willett, J Wu, PJ Vozila, WF Ganong III - US Patent 9,886,944, 2018 - Google Patents
A mobile device is described which is adapted for automatic speech recognition (ASR). A
speech input receives an unknown speech input signal from a user. A local controller …
speech input receives an unknown speech input signal from a user. A local controller …
Multistream network feature processing for a distributed speech recognition system
A distributed voice recognition system and method for obtaining acoustic features and
speech activity at multiple frequencies by extracting high frequency components thereof on a …
speech activity at multiple frequencies by extracting high frequency components thereof on a …