Patents by Inventor Tomasz DORAU
Tomasz DORAU has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11875783Abstract: 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.Type: GrantFiled: June 3, 2020Date of Patent: January 16, 2024Assignee: Intel CorporationInventors: Marcin Terpilowski, Tomasz Dorau, Tobias Bocklet
-
Patent number: 11308978Abstract: 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.Type: GrantFiled: August 5, 2019Date of Patent: April 19, 2022Assignee: INTEL CORPORATIONInventors: Binuraj K. Ravindran, Francis M. Tharappel, Prabhakar R. Datta, Tobias Bocklet, Maciej Muchlinski, Tomasz Dorau, Josef G. Bauer, Saurin Shah, Georg Stemmer
-
Publication number: 20210398535Abstract: A method, system, and article of multiple task audio analysis uses shared audio processing operations.Type: ApplicationFiled: August 31, 2021Publication date: December 23, 2021Applicant: Intel CorporationInventors: Kuba Lopatka, Tomasz Dorau, Maciej Muchlinski
-
Publication number: 20210264898Abstract: Techniques are provided for segmentation of a key phrase. A methodology implementing the techniques according to an embodiment includes accumulating feature vectors extracted from time segments of an audio signal, and generating a set of acoustic scores based on those feature vectors. Each of the acoustic scores in the set represents a probability for a phonetic class associated with the time segments. The method further includes generating a progression of scored model state sequences, each of the scored model state sequences based on detection of phonetic units associated with a corresponding one of the sets of acoustic scores generated from the time segments of the audio signal. The method further includes analyzing the progression of scored state sequences to detect a pattern associated with the progression, and determining a starting and ending point for segmentation of the key phrase based on alignment of the detected pattern with an expected pattern.Type: ApplicationFiled: May 13, 2021Publication date: August 26, 2021Inventors: Tomasz Dorau, Tobias Bocklet, Przemyslaw Tomaszewski, Sebastian Czyryba, Juliusz Norman Chojecki
-
Publication number: 20200294493Abstract: 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.Type: ApplicationFiled: June 3, 2020Publication date: September 17, 2020Applicant: Intel CorporationInventors: Marcin Terpilowski, Tomasz Dorau, Tobias Bocklet
-
Patent number: 10650807Abstract: A method and system are directed to autonomous neural network keyphrase detection and includes generating and using a multiple element state score vector by using neural network operations and without substantial use of a digital signal processor (DSP) to perform the keyphrase detection.Type: GrantFiled: September 18, 2018Date of Patent: May 12, 2020Assignee: Intel CorporationInventors: Tobias Bocklet, Jacek Ossowski, Tomasz Dorau, Maciej Muchlinski, David Pearce, Piotr Rozen
-
Publication number: 20190355379Abstract: 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.Type: ApplicationFiled: August 5, 2019Publication date: November 21, 2019Inventors: Binuraj K. Ravindran, Francis M. Tharappel, Prabhakar R. Datta, Tobias Bocklet, Maciej Muchlinski, Tomasz Dorau, Josef G. Bauer, Saurin Shah, Georg Stemmer
-
Patent number: 10373630Abstract: 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.Type: GrantFiled: March 31, 2017Date of Patent: August 6, 2019Assignee: Intel CorporationInventors: Binuraj K. Ravindran, Francis M. Tharappel, Prabhakar R. Datta, Tobias Bocklet, Maciej Muchlinski, Tomasz Dorau, Josef G. Bauer, Saurin Shah, Georg Stemmer
-
Publication number: 20190043479Abstract: Techniques are provided for segmentation of a key phrase. A methodology implementing the techniques according to an embodiment includes accumulating feature vectors extracted from time segments of an audio signal, and generating a set of acoustic scores based on those feature vectors. Each of the acoustic scores in the set represents a probability for a phonetic class associated with the time segments. The method further includes generating a progression of scored model state sequences, each of the scored model state sequences based on detection of phonetic units associated with a corresponding one of the sets of acoustic scores generated from the time segments of the audio signal. The method further includes analyzing the progression of scored state sequences to detect a pattern associated with the progression, and determining a starting and ending point for segmentation of the key phrase based on alignment of the detected pattern with an expected pattern.Type: ApplicationFiled: May 7, 2018Publication date: February 7, 2019Applicant: INTEL CORPORATIONInventors: Tomasz Dorau, Tobias Bocklet, Przemyslaw Tomaszewski, Sebastian Czyryba, Juliusz Norman Chojecki
-
Publication number: 20190043488Abstract: A method and system are directed to autonomous neural network keyphrase detection and includes generating and using a multiple element state score vector by using neural network operations and without substantial use of a digital signal processor (DSP) to perform the keyphrase detection.Type: ApplicationFiled: September 18, 2018Publication date: February 7, 2019Applicant: Intel CorporationInventors: Tobias Bocklet, Jacek Ossowski, Tomasz Dorau, Maciej Muchlinski, David Pearce, Piotr Rozen
-
Patent number: 10170115Abstract: Key phrase detection techniques for applications such as wake on voice are discussed include performing a vectorized operation on a multiple element acoustic score vector for a current time instance including a single state rejection model score and scores for a multiple state key phrase model and a multiple element state score vector for a previous time instance including a previous state score for the single state rejection model and previous state scores for the multiple state key phrase model to generate a multiple element score summation vector and a second vectorized operation on the multiple element score summation vector to determine a multiple element state score vector for the current time instance. The multiple element state score vector for the current time instance may then be evaluated to determine whether received audio input includes a key phrase corresponding to the multiple state key phrase model.Type: GrantFiled: July 12, 2018Date of Patent: January 1, 2019Assignee: Intel CorporationInventors: Tobias Bocklet, Tomasz Dorau, Przemyslaw Sobon, Przemyslaw Tomaszewski
-
Publication number: 20180322876Abstract: Key phrase detection techniques for applications such as wake on voice are discussed include performing a vectorized operation on a multiple element acoustic score vector for a current time instance including a single state rejection model score and scores for a multiple state key phrase model and a multiple element state score vector for a previous time instance including a previous state score for the single state rejection model and previous state scores for the multiple state key phrase model to generate a multiple element score summation vector and a second vectorized operation on the multiple element score summation vector to determine a multiple element state score vector for the current time instance. The multiple element state score vector for the current time instance may then be evaluated to determine whether received audio input includes a key phrase corresponding to the multiple state key phrase model.Type: ApplicationFiled: July 12, 2018Publication date: November 8, 2018Applicant: Intel CorporationInventors: Tobias BOCKLET, Tomasz DORAU, Przemyslaw SOBON, Przemyslaw TOMASZEWSKI
-
Publication number: 20180286414Abstract: 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.Type: ApplicationFiled: March 31, 2017Publication date: October 4, 2018Inventors: Binuraj K. Ravindran, Francis M. Tharappel, Prabhakar R. Datta, Tobias Bocklet, Maciej Muchlinski, Tomasz Dorau, Josef G. Bauer, Saurin Shah, Georg Stemmer
-
Patent number: 10083689Abstract: Key phrase detection techniques for applications such as wake on voice are discussed include performing a vectorized operation on a multiple element acoustic score vector for a current time instance including a single state rejection model score and scores for a multiple state key phrase model and a multiple element state score vector for a previous time instance including a previous state score for the single state rejection model and previous state scores for the multiple state key phrase model to generate a multiple element score summation vector and a second vectorized operation on the multiple element score summation vector to determine a multiple element state score vector for the current time instance. The multiple element state score vector for the current time instance may then be evaluated to determine whether received audio input includes a key phrase corresponding to the multiple state key phrase model.Type: GrantFiled: December 23, 2016Date of Patent: September 25, 2018Assignee: Intel CorporationInventors: Tobias Bocklet, Tomasz Dorau, Przemyslaw Sobon, Przemyslaw Tomaszewski
-
Publication number: 20180182388Abstract: Key phrase detection techniques for applications such as wake on voice are discussed include performing a vectorized operation on a multiple element acoustic score vector for a current time instance including a single state rejection model score and scores for a multiple state key phrase model and a multiple element state score vector for a previous time instance including a previous state score for the single state rejection model and previous state scores for the multiple state key phrase model to generate a multiple element score summation vector and a second vectorized operation on the multiple element score summation vector to determine a multiple element state score vector for the current time instance. The multiple element state score vector for the current time instance may then be evaluated to determine whether received audio input includes a key phrase corresponding to the multiple state key phrase model.Type: ApplicationFiled: December 23, 2016Publication date: June 28, 2018Inventors: Tobias BOCKLET, Tomasz DORAU, Przemyslaw SOBON, Przemyslaw TOMASZEWSKI
-
Patent number: 9972313Abstract: Techniques related to key phrase detection for applications such as wake on voice are discussed. Such techniques may include intermediate scoring of a state or states of a key phrase model and/or a backward transition or rejection loopback from a state of the key phrase model to a rejection model to reduce false accepts based on received utterances.Type: GrantFiled: March 1, 2016Date of Patent: May 15, 2018Assignee: Intel CorporationInventors: Tobias Bocklet, Adam Marek, Tomasz Dorau, Przemyslaw Sobon
-
Publication number: 20170256255Abstract: Techniques related to key phrase detection for applications such as wake on voice are discussed. Such techniques may include intermediate scoring of a state or states of a key phrase model and/or a backward transition or rejection loopback from a state of the key phrase model to a rejection model to reduce false accepts based on received utterances.Type: ApplicationFiled: March 1, 2016Publication date: September 7, 2017Inventors: Tobias BOCKLET, Adam MAREK, Tomasz DORAU, Przemyslaw SOBON