-
公开(公告)号：US20220115003A1
公开(公告)日：2022-04-14
申请号：US17069462
申请日：2020-10-13
Applicant: Rev.com, Inc.
Inventor： Jean-Philippe Robichaud , Miguel Jette , Joshua Ian Dong , Quinten McNamara , Nishchal Bhandari , Michelle Kai Yu Huang
Abstract: A method of determining an alignment sequence between a reference sequence of symbols and a hypothesis sequence of symbols includes loading a reference sequence of symbols to a computing system and creating a reference finite state automaton for the reference sequence of symbols. The method further includes loading a hypothesis sequence of symbols to the computing system and creating a hypothesis finite state automaton for the hypothesis sequence of symbols. The method further includes traversing the reference finite state automaton, adding new reference arcs and new reference transforming properties arcs and traversing the hypothesis finite state automaton, adding new hypothesis arcs and new hypothesis transforming properties arcs. The method further includes composing the hypothesis finite state automaton with the reference finite state automaton creating alternative paths to form a composed finite state automaton and tracking a number of the alternative paths created. The method further includes pruning the alternative paths based on likely top paths, backtracking over most likely paths of the composed finite state automaton, and rescoring edit-distances of the composed finite state automaton.
-
2.发明公开公开(公告)号：US20230326450A1
公开(公告)日：2023-10-12
申请号：US17656757
申请日：2022-03-28
Applicant: Rev.com, Inc.
Inventor： Jennifer Drexler Fox , Danny Chen , Natalie Delworth
IPC: G10L15/16 , G10L15/22 , G10L15/193 , G06F40/284 , G10L15/06 , G06F40/47
CPC classification number: G10L15/063 , G06F40/284 , G06F40/47 , G10L15/16 , G10L15/193 , G10L15/22
Abstract: A method of adding a custom vocabulary to a transcription system includes receiving a custom vocabulary at an ASIRW module. The method further includes tokenizing the custom vocabulary with the ASIRW module. The method further includes creating a new WFST (weighted finite-state transducer) with the ASIRW module. The method further includes transcribing audio using the new WFST with the ASIRW module. The tokenizing includes performing a translation model on each word of the custom vocabulary
-
Patent Agency Ranking
公开(公告)号：US20210050015A1
公开(公告)日：2021-02-18
申请号：US17087330
申请日：2020-11-02
Applicant: Rev.com, Inc.
IPC: G10L15/26 , G10L19/038 , G10L17/00
Abstract: In one embodiment, a method for transcript generation includes receiving an audio file and dividing it into a plurality of chunks. The method further includes sending each instance of the plurality of chunks to a speech service module. The method further includes converting speech to text for each instance of the plurality of chunks and returning the text for each instance of the plurality of chunks. The method further includes merging the text for each instance of the plurality of chunks to yield an audio file transcript and sending the audio file and chunks to a diarization module. The method further includes performing first pass diarization on the chunks to yield a plurality of diarized chunks and performing second pass diarization on the plurality of diarized chunks and the audio file to yield a diarized audio file. The method further includes merging the files to yield a final transcript.
-
4.发明申请公开(公告)号：US20200135204A1
公开(公告)日：2020-04-30
申请号：US16177061
申请日：2018-10-31
Applicant: Rev.com, Inc.
IPC: G10L15/26 , G10L19/038 , G10L17/00
Abstract: In one embodiment, a method for transcript generation includes receiving an audio file and dividing it into a plurality of chunks. The method further includes sending each instance of the plurality of chunks to a speech service module. The method further includes converting speech to text for each instance of the plurality of chunks and returning the text for each instance of the plurality of chunks. The method further includes merging the text for each instance of the plurality of chunks to yield an audio file transcript and sending the audio file and chunks to a diarization module. The method further includes performing first pass diarization on the chunks to yield a plurality of diarized chunks and performing second pass diarization on the plurality of diarized chunks and the audio file to yield a diarized audio file. The method further includes merging the files to yield a final transcript.
-
公开(公告)号：US12266362B2
公开(公告)日：2025-04-01
申请号：US17087330
申请日：2020-11-02
Applicant: Rev.com, Inc.
Abstract: In one embodiment, a method for transcript generation includes receiving an audio file and dividing it into a plurality of chunks. The method further includes sending each instance of the plurality of chunks to a speech service module. The method further includes converting speech to text for each instance of the plurality of chunks and returning the text for each instance of the plurality of chunks. The method further includes merging the text for each instance of the plurality of chunks to yield an audio file transcript and sending the audio file and chunks to a diarization module. The method further includes performing first pass diarization on the chunks to yield a plurality of diarized chunks and performing second pass diarization on the plurality of diarized chunks and the audio file to yield a diarized audio file. The method further includes merging the files to yield a final transcript.
-
公开(公告)号：US12254866B2
公开(公告)日：2025-03-18
申请号：US17069462
申请日：2020-10-13
Applicant: Rev.com, Inc.
Inventor： Jean-Philippe Robichaud , Miguel Jette , Joshua Ian Dong , Quinten McNamara , Nishchal Bhandari , Michelle Kai Yu Huang
Abstract: A method of determining an alignment sequence between a reference sequence of symbols and a hypothesis sequence of symbols includes loading a reference sequence of symbols to a computing system and creating a reference finite state automaton for the reference sequence of symbols. The method further includes loading a hypothesis sequence of symbols to the computing system and creating a hypothesis finite state automaton for the hypothesis sequence of symbols. The method further includes traversing the reference finite state automaton, adding new reference arcs and new reference transforming properties arcs and traversing the hypothesis finite state automaton, adding new hypothesis arcs and new hypothesis transforming properties arcs. The method further includes composing the hypothesis finite state automaton with the reference finite state automaton creating alternative paths to form a composed finite state automaton and tracking a number of the alternative paths created. The method further includes pruning the alternative paths based on likely top paths, backtracking over most likely paths of the composed finite state automaton, and rescoring edit-distances of the composed finite state automaton.
-
公开(公告)号：US10825458B2
公开(公告)日：2020-11-03
申请号：US16177061
申请日：2018-10-31
Applicant: Rev.com, Inc.
Abstract: In one embodiment, a method for transcript generation includes receiving an audio file and dividing it into a plurality of chunks. The method further includes sending each instance of the plurality of chunks to a speech service module. The method further includes converting speech to text for each instance of the plurality of chunks and returning the text for each instance of the plurality of chunks. The method further includes merging the text for each instance of the plurality of chunks to yield an audio file transcript and sending the audio file and chunks to a diarization module. The method further includes performing first pass diarization on the chunks to yield a plurality of diarized chunks and performing second pass diarization on the plurality of diarized chunks and the audio file to yield a diarized audio file. The method further includes merging the files to yield a final transcript.
-
-
-
-
-
-
Search Results
7
records
(took 0.009 seconds)
