# US 2021/0343291 A1 · Speech-to-text system > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2021/0343291 A1 - Document ID: US20210343291A1 - Status: Published application - Kind: A1 - Application number: 16/865,755 - Filed: 2020-05-04 - Published: 2021-11-04 - Earliest claimed: 2020-05-04 - Assignees: Rovi Guides, Inc. - Applicants: Rovi Guides, Inc. - Inventors: Sukanya Agarwal; Vikram Makam Gupta - Web page: https://patentgrep.com/patent/US20210343291A1 ## CPC - G10L 15/26: Speech to text systems (G10L15/08 takes precedence) - G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue - G10L 15/32: Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems - G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING ## Abstract Systems and methods for processing speech transcription in a speech processing system are disclosed. Transcriptions of utterances is received and identifications to the transcriptions are assigned. In response to receiving an indication of an erroneous transcribed utterance in at least one of the transcriptions, an audio receiver is automatically activated for receiving a second utterance. In response to receiving the second utterance, an audio file of the second utterance and a corresponding identification of the erroneous transcribed utterance are transmitted to a speech recognition system for a second transcription, and the erroneous transcribed utterance is replaced with the second transcription. ## Claims ### Claim 1 A method of processing speech transcription in a speech processing system, the method comprising: receiving a plurality of transcriptions from a plurality of utterances; assigning a plurality of identifications to the plurality of transcriptions; at a control circuitry, in response to receiving an indication of an erroneous transcribed utterance in at least one of the plurality of transcriptions, automatically activating an audio receiver for receiving a second utterance; and in response to receiving the second utterance, at an output circuit, transmitting an audio file of the second utterance and a corresponding identification of the erroneous transcribed utterance to a speech recognition system for a second transcription, wherein the erroneous transcribed utterance is replaced with the second transcription. ### Claim 2 (depends on 1) The method of claim 1, wherein the corresponding identification of the erroneous transcribed utterance is a pointer identifying an utterance location within the plurality of transcriptions. ### Claim 3 (depends on 1) The method of claim 1, wherein the corresponding identification of the erroneous transcribed utterance is an utterance location within the plurality of transcriptions. ### Claim 4 (depends on 1) The method of claim 1, further comprising the control circuitry, in response to receiving a plurality of transcriptions from a plurality of utterances, parsing the plurality of transcriptions into a plurality of transcribed utterances. ### Claim 5 (depends on 4) The method of claim 4, wherein assigning the plurality of identifications to the plurality of transcriptions comprises assigning each of the plurality of transcriptions a corresponding identification uniquely identifying a location of a transcribed utterance within the plurality of transcriptions. ### Claim 6 (depends on 1) The method of claim 1, further including receiving the indication of the erroneous transcribed utterance at an input circuitry of a computing device. ### Claim 7 (depends on 1) The method of claim 1, wherein the indication of the erroneous transcribed utterance is a screen highlight of the erroneous transcribed utterance. ### Claim 8 (depends on 1) The method of claim 1, wherein transmitting an audio file of the second utterance and a corresponding identification of the erroneous transcribed utterance to a speech recognition system for a second transcription comprises transmitting the audio file to an automated speech recognition service. ### Claim 9 (depends on 1) The method of claim 1, further comprising receiving the second utterance in response to automatically activating the audio receiver. ### Claim 10 (depends on 1) The method of claim 1, wherein automatically activating the audio receiver comprises automatically activating a microphone feature of a personal computer or a tablet. ### Claim 11 (depends on 1) The method of claim 1, wherein the first transcription corresponds to a long dictation, and wherein the long dictation is received at a personal computer or a tablet. ### Claim 12 (canceled) ### Claim 13 A system of processing speech transcription in a speech processing system, the system comprising: input circuitry configured to receive a plurality of transcriptions from a plurality of utterances; control circuitry configured to assign a plurality of identifications to the plurality of transcriptions; the control circuitry, in response to receiving an indication of an erroneous transcribed utterance in at least one of the plurality of transcriptions, further configured to automatically activate an audio receiver for receiving a second utterance; and output circuitry that in response to receiving the second utterance is configured to transmit an audio file of the second utterance and a corresponding identification of the erroneous transcribed utterance to a speech recognition system for a second transcription, wherein the erroneous transcribed utterance is replaced with the second transcription. ### Claim 14 (depends on 13) The system of claim 13, wherein the corresponding identification of the erroneous transcribed utterance is a pointer identifying an utterance location within the plurality of transcriptions. ### Claim 15 (depends on 13) The system of claim 13, wherein the corresponding identification of the erroneous transcribed utterance is an utterance location within the plurality of transcriptions. ### Claim 16 (depends on 13) The system of claim 13, wherein the control circuitry, in response to receiving a plurality of transcriptions from a plurality of utterances, is configured to parse the plurality of transcriptions into a plurality of transcribed utterances. ### Claim 17 (depends on 13) The system of claim 13, wherein in assigning the plurality of identifications to the plurality of transcriptions, the control circuitry is further configured to assign each of the plurality of transcriptions a corresponding identification uniquely identifying a location of a transcribed utterance within the plurality of transcriptions. ### Claim 18 (depends on 13) The system of claim 13, wherein the input circuitry is configured to receive an indication of the erroneous transcribed utterance. ### Claim 19 (depends on 18) The system of claim 18, wherein the indication of the erroneous transcribed utterance is a screen highlight of the erroneous transcribed utterance. ### Claim 20 (depends on 13) The system of claim 13, wherein the output circuitry is configured to transmit an audio file of the second utterance and a corresponding identification of the erroneous transcribed utterance to a speech recognition system for a second transcription comprises transmitting the audio file to an automated speech recognition service. ### Claim 21 (depends on 13) The system of claim 13, wherein the input circuitry is configured to receive the second utterance in response to the control circuitry automatically activating the audio receiver. ### Claim 22 (depends on 13) The system of claim 13, wherein in automatically activating the audio receiver, the control circuitry is further configured to automatically activate a microphone feature of a personal computer or a tablet. ### Claim 23 (depends on 13) The system of claim 13, wherein the first transcription corresponds to a long dictation, and wherein the long dictation is received at a personal computer or a tablet. ### Claim 24 (canceled)