Intel Corporation

Tobias Bocklet

Joachim Hofer

Tomasz Dorau

Kuba Lopatka

Georg Stemmer

Josef G Bauer

Munir Georges

Jonathan J Huang

Jacek Ossowski

Maciej Muchlinski

David Pearce

Przemyslaw Sobon

Saurin Shah

Francis M Tharappel

Binuraj K Ravindran

Piotr Rozen

Munir Nikolai Alexander Georges

Adam Marek

Prabhakar R Datta

Sebastian Czyryba

Mateusz Kotarski

Przemyslaw Tomaszewski

Josef Bauer

Wenda Chen

Muhammad M Khellah

Gokcen Cilingir

Charles Augustine

Somnath Paul

Turbo Majumder

Suyoung Bang

Mithil Ramteke

Wootaek Lim

Jakub Nowicki

Krzysztof Czarnowski

Marek Zabkiewicz

Sivasubramanian Sundaram

Marcin Terpilowski

Sarang Akotkar

An example apparatus for recognizing speech includes an audio receiver to receive a stream of audio. The apparatus also includes a key phrase detector to detect a key phrase in the stream of audio. The apparatus further includes a model adapter to dynamically adapt a model based on the detected key phrase. The apparatus also includes a query recognizer to detect a voice query following the key phrase in a stream of audio via the adapted model.

Adaptively recognizing speech using key phrases

A method, system, and device are directed to audio input bit-size conversion for compatibility to audio processing systems with an expected input sample bit-size.

Method and system of audio input bit-size conversion for audio processing

Techniques related to a method and system of audio false keyphrase rejection using speaker recognition are described herein. Such techniques use speaker recognition of a computer originated voice to omit actions triggered when a keyphrase is present in captured audio and omitted when speech of the captured audio was spoken by the computer originated voice.

Method and system of audio false keyphrase rejection using speaker recognition

Methods, apparatus, systems and articles of manufacture for recognizing speech are disclosed. An example system includes one or more processors to execute instructions to: identify a plurality of phonemes in a speech signal; perform a comparison of a subset of the phonemes to a phonetic string, the phonetic string representative of at least a portion of a wake up phrase; determine if one or more of the phonemes of the subset correspond to the wake up phrase based on the comparison; and generate a hypothesis of a command included in the speech signal by excluding the wake up phrase when one or more of the phonemes of the subset correspond to the wake up phrase or a portion of the wake up phrase.

Automatic speech recognition with filler model processing

An embodiment of a spoken intent detection device includes technology to detect a phrase in an electronic representation of an audio stream based on a pre-defined vocabulary, associate a time stamp with the detected phrase, and classify a spoken intent based on a sequence of detected phrases and the respective associated time stamps. Other embodiments are disclosed and claimed.

Time asynchronous spoken intent detection

A computer-implemented method of false keyphrase rejection comprises receiving a captured audio signal of human speech including one or more keyphrases that trigger an action. It also comprises detecting whether or not at least part of the speech is spoken by at least one computer originated voice. The method also has an operation of omitting the triggering of the action at least partly due to the computer originated voice being recognized in the speech.

Methods, apparatus, systems and articles of manufacture are disclosed for distributed automatic speech recognition. An example apparatus includes a detector to process an input audio signal and identify a portion of the input audio signal including a sound to be evaluated, the sound to be evaluated organized into a plurality of audio features representing the sound. The example apparatus includes a quantizer to process the audio features using a quantization process to reduce the audio features to generate a reduced set of audio features for transmission. The example apparatus includes a transmitter to transmit the reduced set of audio features over a low-energy communication channel for processing.

Systems and methods for energy efficient and low power distributed automatic speech recognition on wearable devices

Techniques are provided for acoustic event detection. A methodology implementing the techniques according to an embodiment includes extracting acoustic features from a received audio signal. The acoustic features may include, for example, one or more short-term Fourier transform frames, or other spectral energy characteristics, of the audio signal. The method also includes applying a trained classifier to the extracted acoustic features to identify and label acoustic event subparts of the audio signal and to generate scores associated with the subparts. The method further includes performing sequence decoding of the acoustic event subparts and associated scores to detect target acoustic events of interest based on the scores and temporal ordering sequence of the event subparts. The classifier is trained on acoustic event subparts that are generated through unsupervised subspace clustering techniques applied to training data that includes target acoustic events.

Acoustic event detection based on modelling of sequence of event subparts

Techniques related to keyphrase detection for applications such as wake on voice are disclosed herein. Such techniques may have high accuracy by using scores of phone positions in triphones to select which triphones to use with a rejection model, using context-related phones for the rejection model, adding silence before keyphrase sounds for a keyphrase model, or any combination of these.

Method and system of high accuracy keyphrase detection for low resource devices

An automatic speech recognition (ASR) system includes a memory configured to store a filler model. The filler model includes one or more phonetic strings corresponding to one or more portions of a wake up phrase. The ASR system also includes one or more processors operatively coupled to the memory and configured to analyze a speech signal with the filler model to determine whether the speech signal includes the wake up phrase or any portion of the wake up phrase. The one or more processors are also configured to generate, based on the analysis, a hypothesis of underlying speech included in the speech signal. The hypothesis excludes the wake up phrase or any portion of the wake up phrase included in the speech signal.

An embodiment of a wake-on-intent speech recognition device includes technology to detect one or more keywords in a digital representation of a spoken natural language utterance, determine an intent of the spoken natural language utterance based on the detected keywords, and provide the spoken natural language utterance to a speech recognition and interpretation system if the determined intent is to further process the spoken natural language utterance. Other embodiments are disclosed and claimed.

Spoken keyword detection based utterance-level wake on intent system

Techniques related to key phrase detection for applications such as wake on voice are discussed. Such techniques may include updating a start state based rejection model and a key phrase model based on scores of sub-phonetic units from an acoustic model to generate a rejection likelihood score and a key phrase likelihood score and determining whether received audio input is associated with a predetermined key phrase based on the rejection likelihood score and the key phrase likelihood score.

Low resource key phrase detection for wake on voice

Techniques related to a method and system of robust speaker recognition activation are described herein. Such techniques apply keyphrase detection and speaker recognition to a subsequent phrase after detecting a waking keyphrase.

Method and system of robust speaker recognition activation

Techniques are provided for efficient acoustic event detection with reduced resource consumption. A methodology implementing the techniques according to an embodiment includes calculating frames of power spectra based on segments of received acoustic signals. The method further includes two processes, one for detecting impulsive acoustic events and another for detecting continuous acoustic events. The first process includes generating impulsive acoustic event features associated with first and second power spectrum frames, applying a neural network classifier to the impulsive acoustic event features to generate event scores, and detecting an impulsive acoustic event based on those event scores. The second process includes generating reduced-dimension continuous acoustic event features associated with the first and second power spectrum frames, applying a neural network classifier to the reduced-dimension continuous acoustic event features to generate a second set of event scores, and detecting a continuous acoustic event based on the second set of event scores.

Growing community of inventors

Munich, Germany

Tobias Bocklet