Search

Petar S Aleksic

from Jersey City, NJ
Age ~50
Get Report
Related to:
Stanisa B AleksicBozidar S Aleksic, 61Dragica M Aleksic
Connected to:
Brooke L Aleksic, 61Gordana Aleksic, 60Jelena Aleksich, 34Jovanka Aleksic, 67Mirko Aleksic, 69Paul B Aleksich, 87Sinisa Aleksic, 53Stefan Aleksic, 28Svetlana Aleksic, 68Aleksandra A Aleksieva, 36

Petar Aleksic Phones & Addresses

  • 104 Mercer St, Jersey City, NJ 07302 (201) 946-0965
  • 1915 Wesley Ave, Evanston, IL 60201
  • 739 Hinman Ave, Evanston, IL 60202 (847) 424-9438
  • Chicago, IL
  • New York, NY

Resumes

Resumes

Petar Aleksic Photo 1

Petar Aleksic

View page
Location:
Jersey City, NJ
Industry:
Electrical/Electronic Manufacturing
Petar Aleksic Photo 2

Petar Aleksic

View page
Location:
Chicago, IL
Industry:
Telecommunications

Publications

Us Patents

Mixed Model Speech Recognition

View page
US Patent:
20130346078, Dec 26, 2013
Filed:
Mar 15, 2013
Appl. No.:
13/838379
Inventors:
Petar Aleksic - Jersey City NJ, US
International Classification:
G10L 15/26
US Classification:
704235
Abstract:
In one aspect, a method comprises accessing audio data generated by a computing device based on audio input from a user, the audio data encoding one or more user utterances. The method further comprises generating a first transcription of the utterances by performing speech recognition on the audio data using a first speech recognizer that employs a language model based on user-specific data. The method further comprises generating a second transcription of the utterances by performing speech recognition on the audio data using a second speech recognizer that employs a language model independent of user-specific data. The method further comprises determining that the second transcription of the utterances includes a term from a predefined set of one or more terms. The method further comprises, based on determining that the second transcription of the utterance includes the term, providing an output of the first transcription of the utterance.

Realtime Acoustic Adaptation Using Stability Measures

View page
US Patent:
8515750, Aug 20, 2013
Filed:
Sep 19, 2012
Appl. No.:
13/622576
Inventors:
Petar Aleksic - Jersey City NJ, US
Assignee:
Google Inc. - Mountain View CA
International Classification:
G10L 15/26
US Classification:
704235, 7042701, 704244, 704254, 704245, 379 8801, 379 8802
Abstract:
Methods, systems, and computer programs encoded on a computer storage medium for real-time acoustic adaptation using stability measures are disclosed. The methods include the actions of receiving a transcription of a first portion of a speech session, wherein the transcription of the first portion of the speech session is generated using a speaker adaptation profile. The actions further include receiving a stability measure for a segment of the transcription and determining that the stability measure for the segment satisfies a threshold. Additionally, the actions include triggering an update of the speaker adaptation profile using the segment, or using a portion of speech data that corresponds to the segment. And the actions include receiving a transcription of a second portion of the speech session, wherein the transcription of the second portion of the speech session is generated using the updated speaker adaptation profile.

Contextual Denormalization For Automatic Speech Recognition

View page
US Patent:
20220277749, Sep 1, 2022
Filed:
Feb 28, 2022
Appl. No.:
17/652923
Inventors:
- Mountain View CA, US
Petar Aleksic - Jersey City NJ, US
Pedro J. Moreno Mengibar - Jersey City NJ, US
Assignee:
Google LLC - Mountain View CA
International Classification:
G10L 15/26
G06F 40/56
G10L 15/22
Abstract:
A method includes receiving a speech input from a user and obtaining context metadata associated with the speech input. The method also includes generating a raw speech recognition result corresponding to the speech input and selecting a list of one or more denormalizers to apply to the generated raw speech recognition result based on the context metadata associated with the speech input. The generated raw speech recognition result includes normalized text. The method also includes denormalizing the generated raw speech recognition result into denormalized text by applying the list of the one or more denormalizers in sequence to the generated raw speech recognition result.

Mixed Model Speech Recognition

View page
US Patent:
20220262365, Aug 18, 2022
Filed:
May 3, 2022
Appl. No.:
17/661837
Inventors:
- Mountain View CA, US
Petar Aleksic - Jersey City NJ, US
Assignee:
Google LLC - Mountain View CA
International Classification:
G10L 15/26
G10L 15/18
G10L 15/22
G10L 15/32
G10L 15/30
Abstract:
In one aspect, a method comprises accessing audio data generated by a computing device based on audio input from a user, the audio data encoding one or more user utterances. The method further comprises generating a first transcription of the utterances by performing speech recognition on the audio data using a first speech recognizer that employs a language model based on user-specific data. The method further comprises generating a second transcription of the utterances by performing speech recognition on the audio data using a second speech recognizer that employs a language model independent of user-specific data. The method further comprises determining that the second transcription of the utterances includes a term from a predefined set of one or more terms. The method further comprises, based on determining that the second transcription of the utterance includes the term, providing an output of the first transcription of the utterance.

Word Lattice Augmentation For Automatic Speech Recognition

View page
US Patent:
20220229992, Jul 21, 2022
Filed:
Jan 31, 2022
Appl. No.:
17/589186
Inventors:
- Mountain View CA, US
Petar Aleksic - Jersey City NJ, US
Pedro Moreno - Jersey City NJ, US
International Classification:
G06F 40/295
G06F 40/30
G10L 15/06
G10L 15/187
G10L 15/22
Abstract:
Speech processing techniques are disclosed that enable determining a text representation of named entities in captured audio data. Various implementations include determining the location of a carrier phrase in a word lattice representation of the captured audio data, where the carrier phrase provides an indication of a named entity. Additional or alternative implementations include matching a candidate named entity with the portion of the word lattice, and augmenting the word lattice with the matched candidate named entity.

Language Model Biasing Modulation

View page
US Patent:
20230109903, Apr 13, 2023
Filed:
Dec 12, 2022
Appl. No.:
18/064917
Inventors:
- Mountain View CA, US
Petar Aleksic - Jersey City NJ, US
Assignee:
Google LLC - Mountain View CA
International Classification:
G10L 15/07
G10L 15/197
G10L 15/183
G10L 15/24
Abstract:
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for modulating language model biasing. In some implementations, context data is received. A likely context associated with a user is determined based on at least a portion of the context data. One or more language model biasing parameters based at least on the likely context associated with the user is selected. A context confidence score associated with the likely context based on at least a portion of the context data is determined. One or more language model biasing parameters based at least on the context confidence score is adjusted. A baseline language model based at least on the one or more of the adjusted language model biasing parameters is biased. The baseline language model is provided for use by an automated speech recognizer (ASR).

Allowing Spelling Of Arbitrary Words

View page
US Patent:
20210350074, Nov 11, 2021
Filed:
Jul 24, 2021
Appl. No.:
17/443330
Inventors:
- Mountain View CA, US
Gleb Skobeltsyn - Kilchberg, CH
Jakob Nicolaus Foerster - San Francisco CA, US
Petar Aleksic - Jersey City NJ, US
Assaf Avner Hurwitz Michaely - Long Island City NY, US
Assignee:
Google LLC - Mountain View CA
International Classification:
G06F 40/232
G10L 15/32
G10L 15/26
G10L 15/197
G10L 15/187
G10L 15/22
G06F 3/16
G10L 15/19
G10L 15/30
Abstract:
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for natural language processing. One of the methods includes receiving a first voice input from a user device; generating a first recognition output; receiving a user selection of one or more terms in the first recognition output; receiving a second voice input spelling a correction of the user selection; determining a corrected recognition output for the selected portion; and providing a second recognition output that merges the first recognition output and the corrected recognition output.

Server Side Hotwording

View page
US Patent:
20210287678, Sep 16, 2021
Filed:
Jun 2, 2021
Appl. No.:
17/337182
Inventors:
- Mountain View CA, US
Petar Aleksic - Jersey City NJ, US
Johan Schalkwyk - Scarsdale NY, US
Pedro J. Moreno Mengibar - Jersey City NJ, US
Assignee:
GOOGLE LLC - Mountain View CA
International Classification:
G10L 15/30
G10L 15/32
G10L 15/26
Abstract:
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for detecting hotwords using a server. One of the methods includes receiving an audio signal encoding one or more utterances including a first utterance; determining whether at least a portion of the first utterance satisfies a first threshold of being at least a portion of a key phrase; in response to determining that at least the portion of the first utterance satisfies the first threshold of being at least a portion of a key phrase, sending the audio signal to a server system that determines whether the first utterance satisfies a second threshold of being the key phrase, the second threshold being more restrictive than the first threshold; and receiving tagged text data representing the one or more utterances encoded in the audio signal when the server system determines that the first utterance satisfies the second threshold.
Control profile
Petar S Aleksic from Jersey City, NJ, age ~50 Get Report