Patents Assigned to FTR Labs Pty Ltd
-
Patent number: 11900947Abstract: Embodiments of the present invention provide methods and systems for performing automatic diarisation of sound recordings including speech from one more speakers. The automatic diarisation has a development or training phase and a utilisation or evaluation phase. In the development or training phase background models and hyperparameters are generated from already annotated sound recordings. These models and hyperparameters are applied during the evaluation or utilisation phase to diarise new or not previously diarised or annotated recordings.Type: GrantFiled: February 24, 2021Date of Patent: February 13, 2024Assignee: FTR LABS PTY LTDInventors: Houman Ghaemmaghami, Shahram Kalantari, David Dean, Subramanian Sridharan
-
Patent number: 10680803Abstract: A system for verifying a recording. The system comprises at least one processor, at least one non-transitory computer readable storage medium storing instructions thereon that, when executed by the at least one processor, cause the system to verify an electronic recording file comprising a cryptographic hash function based on the recording and generated by a first electronic device, verifying the electronic recording file comprises generating a pair of certification requests. A first of the pair of certification requests is based on the cryptographic hash function, and a second of the pair of certification requests is based on the cryptographic hash function in combination with one or more further pieces of data associated with the recording.Type: GrantFiled: October 23, 2019Date of Patent: June 9, 2020Assignee: FTR Labs Pty LtdInventors: Marc Jonathan Uldridge, Anthony Douglass
-
Publication number: 20200059355Abstract: A system for verifying a recording. The system comprises at least one processor, at least one non-transitory computer readable storage medium storing instructions thereon that, when executed by the at least one processor, cause the system to verify an electronic recording file comprising a cryptographic hash function based on the recording and generated by a first electronic device, verifying the electronic recording file comprises generating a pair of certification requests. A first of the pair of certification requests is based on the cryptographic hash function, and a second of the pair of certification requests is based on the cryptographic hash function in combination with one or more further pieces of data associated with the recording.Type: ApplicationFiled: October 23, 2019Publication date: February 20, 2020Applicant: FTR Labs Pty LtdInventors: Marc Jonathan Uldridge, Anthony Douglass
-
Patent number: 10476666Abstract: A method for verifying a recording comprising the steps of: a) Creating the recording using a first electronic device; b) Generating, using the first electronic device, an electronic recording file, the electronic recording file comprising information based on the recording and one or more further pieces of data associated with the recording; c) Sending, using the first electronic device, the electronic recording file to a certification server; d) Generating, using the certification server, one or more certification requests based on at least a portion of the information in the electronic recording file, and sending the one or more certification requests to a blockchain; e) Receiving, with the certification server, confirmation of the approval of the one or more certification requests by the blockchain; and f) Generating and/or displaying a verification confirmation on the first electronic device.Type: GrantFiled: September 10, 2018Date of Patent: November 12, 2019Assignee: FTR Labs Pty LtdInventors: Marc Jonathan Uldridge, Anthony Douglass
-
Publication number: 20190304470Abstract: Embodiments of the present invention provide methods and systems for performing automatic diarisation of sound recordings including speech from one more speakers. The automatic diarisation has a development or training phase and a utilisation or evaluation phase. In the development or training phase background models and hyperparameters are generated from already annotated sound recordings. These models and hyperparameters are applied during the evaluation or utilisation phase to diarise new or not previously diarised or annotated recordings.Type: ApplicationFiled: July 11, 2017Publication date: October 3, 2019Applicant: FTR LABS PTY LTDInventors: Houman GHAEMMAGHAMI, Shahram KALANTARI, David DEAN, Subramanian SRIDHARAN
-
Publication number: 20190081774Abstract: A method for verifying a recording comprising the steps of: a) Creating the recording using a first electronic device; b) Generating, using the first electronic device, an electronic recording file, the electronic recording file comprising information based on the recording and one or more further pieces of data associated with the recording; c) Sending, using the first electronic device, the electronic recording file to a certification server; d) Generating, using the certification server, one or more certification requests based on at least a portion of the information in the electronic recording file, and sending the one or more certification requests to a blockchain; e) Receiving, with the certification server, confirmation of the approval of the one or more certification requests by the blockchain; and f) Generating and/or displaying a verification confirmation on the first electronic device.Type: ApplicationFiled: September 10, 2018Publication date: March 14, 2019Applicant: FTR Labs Pty LtdInventors: Marc Jonathan Uldridge, Anthony Douglass