Intel Corporation

Michael E Deisher

Ohad Falik

Lakshman Krishnamurthy

Chaitanya Sreerama

Francis M Tharappel

Keith Raynard Tinsley

Prabhakar R Datta

Saurabh Dadu

Harry G Skinner

Robert Conrad Knauerhase

Saurin Shah

Willem M Beltman

Mandar S Joshi

Brian Kenneth Vogel

Arijit Raychowdhury

Bryan R Peebler

Jenny Chang

Michael E Kounavis

Ravishankar Iyer

James W Tschanz

Giuseppe Beppe Raffa

David L Graumann

Gokcen Cilingir

Anand P Rangarajan

Moshe Wasserblat

Lama Nachman

Stephen H Hall

Robert William Morris

Georg Stemmer

Carlos Alfonso Tokunaga

Zhenyu Zhu

Srikanth Potluri

Devon Worrell

Rajesh P Banginwar

Thomas E Walsh

Jeffrey N Kidder

Sean J W Lawrence

Sylvia Downing

Guillermo Perez

Hai Ming Khor

Tao Ma

Russell E Henning

Ioannis Yannis Schoinas

Gabriel Amores

Darryl Adams

Matias Zanartu

Haicheng Zhou

Loic Dufresne De Virel

Nikhil Pantpratinidhi

An apparatus for applying dynamic quantization of a neural network is described herein. The apparatus includes a scaling unit and a quantizing unit. The scaling unit is to calculate an initial desired scale factors of a plurality of inputs, weights and a bias and apply the input scale factor to a summation node. Also, the scaling unit is to determine a scale factor for a multiplication node based on the desired scale factors of the inputs and select a scale factor for an activation function and an output node. The quantizing unit is to dynamically requantize the neural network by traversing a graph of the neural network.

Dynamic quantization of neural networks

Computing platforms and related methods for providing accessible user interfaces are disclosed. An example apparatus includes a display controller to a display controller to sample a region of a display frame associated with a location of a touch on a display screen of a user device and logic circuitry to, after a Basic Input Output System (BIOS) is operational in the user device and prior to loading of an operating system of the user device, identify content in the display region and cause at least one output device to generate an output representative of the content, the output including at least one of an audible output or a haptic output.

Computing platforms and related methods for providing accessible user interfaces

An apparatus for speech model with personalization via ambient context harvesting, is described herein. The apparatus includes a microphone, context harvesting module, confidence module, and training module. The context harvesting module is to determine a context associated with the captured audio signals. A confidence module is to determine a confidence of the context as applied to the audio signals. A training module is to train a neural network in response to the confidence being above a predetermined threshold.

Speech model personalization via ambient context harvesting

Systems, apparatus and methods are described including operations for a flexible neural network accelerator.

Flexible neural network accelerator and methods therefor

Systems, apparatus and methods are described including operations for a dual mode GMM (Gaussian Mixture Model) scoring accelerator for both speech and video data.

Speech and video dual mode gaussian mixture model scoring accelerator

Techniques are disclosed for reliably masking speech commands directed to one or more computing devices to prevent the speech commands from being rendered. In some embodiments, each of the one or more computing devices includes components configured to generate acoustic data from ambient sound waves, process the acoustic data to identify a speech command sequence, and mask the speech command sequence from being rendered. At least some of the systems and methods disclosed herein monitor inbound audio at a fine grain level of detail. Working at this level of granularity enables the system and methods described herein to detect potential speech commands early within the user's utterance thereof and to discriminate quickly between true speech commands and other user utterances. These early detection and discrimination features, in turn, enable some embodiments to manage potential communication disruptions (e.g., jitter and/or latency) by modifying rates of audio prior to rendering.

Voice command masking systems and methods

A language model is modified for a local speech recognition system using remote speech recognition sources. In one example, a speech utterance is received. The speech utterance is sent to at least one remote speech recognition system. Text results corresponding to the utterance are received from the remote speech recognition system. A local text result is generated using local vocabulary. The received text results and the generated text result are compared to determine words that are out of the local vocabulary and the local vocabulary is updated using the out of vocabulary words.

Language model modification for local speech recognition systems using remote sources

Technologies are described herein that allow a user to wake up a computing device operating in a low-power state and for the user to be verified by speaking a single wake phrase. Wake phrase recognition is performed by a low-power engine. In some embodiments, the low-power engine may also perform speaker verification. In other embodiments, the mobile device wakes up after a wake phrase is recognized and a component other than the low-power engine performs speaker verification on a portion of the audio input comprising the wake phrase. More than one wake phrases may be associated with a particular user, and separate users may be associated with different wake phrases. Different wake phrases may cause the device transition from a low-power state to various active states.

Mechanism and apparatus for seamless voice wake and speaker verification

Systems, apparatus and methods are described including operations for memory access via direct memory access engines, of a Gaussian Mixture Model Accelerator, corresponding to individual data streams.

Gaussian mixture model accelerator with direct memory access engines corresponding to individual data streams

A disclosed speech processor includes a front end to receive a speech input and generate a feature vector indicative of a portion of the speech input and a Gaussian mixture (GMM) circuit to receive the feature vector, model any one of a plurality of GMM speech recognition algorithms, and generate a GMM score for the feature vector based on the GMM speech recognition algorithm modeled. In at least one embodiment, the GMM circuit includes a common compute block to generate feature a vector sum indicative of a weighted sum of differences squares between the feature vector and a mixture component of the GMM speech recognition algorithm. In at least one embodiment, the GMM speech recognition algorithm being modeled includes a plurality of Gaussian mixture components and the common compute block is operable to generate feature vector scores corresponding to each of the plurality of mixture components.

Flexible architecture for acoustic signal processing engine

Methods of enabling voice processing with minimal power consumption includes recording time-domain audio signal at a first clock frequency and a first voltage, and performing Fast Fourier Transform (FFT) operations on the time-domain audio signal at a second clock frequency to generate frequency-domain audio signal. The frequency domain audio signal may be enhanced to obtain better signal to noise ratio, through one or multiple filtering and enhancing techniques. The enhanced audio signal may be used to generate the total signal energy and estimate the background noise energy. Decision logic may determine from the signal energy and the background noise, the presence or absence of the human voice. The first clock frequency may be different from the second clock frequency.

Low power voice detection

In some embodiments an accelerometer is mechanically coupled to a first device. The accelerometer obtains a vibration profile in response to a relative movement of the first device and a second device. A radio transmits an encrypted version of the vibration profile to the second device and receives an encrypted version of a vibration profile from the second device. A processor sets up a secure channel between the radio and the second device in which to exchange keys with the second device in order to decrypt the received encrypted vibration profile. The processor also decrypts the received encrypted vibration profile in response to at least one of the exchanged keys, compares the transmitted vibration profile with the received vibration profile and allows a sharing of resources with the second device if a match occurs between the transmitted vibration profile and the received vibration profile. Other embodiments are described and claimed.

Handheld device association via shared vibration

In some embodiments a phase between a periodic spreading signal and an effective spreading signal modulating an interfering harmonic is determined, an amplitude of the interfering harmonic is estimated, and the interfering harmonic is canceled from a received signal. Other embodiments are described and claimed.

Removal of modulated tonal interference

Growing community of inventors

Hillsboro, OR, United States of America

Michael E Deisher