Enco captions reach Canada's accuracy standard at Pattison stations

Researchers who analyzed reports to the CRTC found that Pattison's automatic Enco captions were slightly below Canada's standard in 2019-2020 and consistently above it in 2020-2021.

  • 2 for a person

    The study reports that the broadcaster's automatic captions went from too variable and slightly below the standard in 2019-2020 to consistently above it in 2020-2021.

Depth runs from 1, a convenience or time saved, to 5, a life or a livelihood preserved.

Status
Reported benefit.
Evidence

foundstudiedreportedclaimed

An independent peer-reviewed study supports the benefit.

Compared with

The broadcaster's automatic captions in 2019-2020. Measured.

The system’s part
Not isolated. The NER scores measure captions that Enco's software produced with no captioner at broadcast time, but no document compares the same programs captioned by people. Staff word lists and newsroom scripts loaded before broadcast contributed to the gains. The study describes Enco's product as speech recognition software but does not show that it learns from data. ENCO describes its enCaption software as AI that combines machine learning with speech-to-text conversion.
Not yet checked
LimitsCosts and harmsLearns from dataLater outcome

Download data Cite Suggest a correction

Benefit type
Improved Accessibility
System
Enco automated captioning software for live local programs (fully automatic captions)
Made by
ENCO Systems (Enco), product not named in the study
Used by
Jim Pattison Broadcast Group Limited Partnership
Where
Kamloops and Prince George (British Columbia) and Medicine Hat (Alberta), Canada
Stage
In routine use
Date
, when the source was published
Kind
Aggregate result
Broad benefit
Documenting/Recording Information
Collections
Scrutiny and findings, Cross-border records
Last revised
1 November 2026

Sources

  1. Peer-reviewed study, by authors with no tie to the system.

    Romero-Fresco P, Fresno N. The accuracy of automatic and human live captions in English. Linguistica Antverpiensia, New Series: Themes in Translation Studies 22 (2023): 114-133, section 3.4 (case study 4: live TV captions in Canada). Published 13 December 2023. doi:10.52034/lans-tts.v22i.774.

    for the first time, broadcasters such as Jim Pattison Broadcast Group and The Miracle Channel Associations consistently reach accuracy rates above the required threshold in 2020-2021. Impressively, of the 55 samples analysed by these two broadcasters in 2020-2021, 52 reached 98%.
    By 2021, in the second round of live captions analysed in Canada, the lowest accuracy rates obtained in the 31 samples analysed by Jim Pattison Broadcast Group and in the 24 samples analysed by The Miracle Channel Associations were 97.8% and 97.9%, respectively.
    meeting regularly with Enco, the manufacturer of the captioning software, to review the accuracy reports;
    They are also more accurate than automatic captions, which feature more samples below 98% accuracy and fewer samples exceeding a 99% accuracy rate (60% of the automatic samples did not reach the minimum threshold and only 1% featured an excellent accuracy).

  2. Regulatory document, by authors with no tie to the system. Context or contrary evidence.

    Canadian Radio-television and Telecommunications Commission. Broadcasting Regulatory Policy CRTC 2019-308: English-language closed captioning mandatory quality standards relating to the accuracy rate for live television programming. Ottawa, 30 August 2019. Archived copy of https://crtc.gc.ca/eng/archive/2019/2019-308.htm. Appendix 1, Quality Standard 3.

    Beginning 1 March 2020, broadcasters must reach an accuracy rate of at least 98 for English-language closed captioning of live television programming
    Further, E-ILTS acknowledged that voice recognition software, which is sometimes used by independent television stations and allows for costs savings, is improving year by year, but noted that based on preliminary testing, voice recognition-based captioning could have difficulty meeting the proposed NER 98 accuracy standard in the short term.
    Jim Pattison Broadcast Group Limited Partnership, operating in Kamloops and Prince George, British Columbia, and Medicine Hat, Alberta; Stingray Digital Group Inc. (now Stingray Group Inc.) in Lloydminster, Alberta; Thunder Bay Electronics Limited in Thunder Bay, Ontario; The Miracle Channel Association in Lethbridge, Alberta;

  3. Other, by the makers. Context or contrary evidence.

    ENCO Systems. enCaption product page (enco.com). Accessed 1 November 2026.

    enCaption is an AI software solution that automatically generates captions and time-stamped transcripts on-premise, in the Cloud or as a hybrid solution. Our captioning approach combines machine learning with advanced speech-to-text conversion and grammatical structure analysis to deliver exceptional accuracy with extremely low latency.

Details

AI system

Workflow

Enco's software produced fully automatic captions for the broadcaster's live programs. Managers met regularly with Enco to review the accuracy reports. Staff added commonly used words and local names to the software each month and removed words no longer needed. Newsroom scripts were loaded into the captioning software before broadcast.

Follow-up

Conditions for replication

Live English-language captions must score at least 98 under the Canadian NER guidelines, as calculated by certified evaluators. Remote news and panel discussions need particular care, since poor audio, cross talk and fast speech affect automatic captions. Automatic captions need effective human help to reach the threshold regularly.

Entry details

Sector

Broadcasting / live closed captions for deaf and hard-of-hearing viewers.

Purpose

Enco built its captioning software to turn the speech in live programs into closed captions automatically.

31 more questions not yet checked

model, release, provider, role, configuration, inputs and outputs, autonomy, human oversight, AI contribution, beneficiaries, reach, distribution and access, duration, every measurement question, every money question, ownership and control, dependencies, cross-border connections, geopolitical implications, replication attempts, availability, institutional decision, grounds, action and result, success criterion, every evidence question, observed or intended, alternative assessments, related entries, other identifiers, category mappings.

Cite this record

Peter H. Vartanian. (2026). Enco captions reach Canada's accuracy standard at Pattison stations (AIBD-1148). Artificial Intelligence Benefits Database, edition of 1 November 2026. https://petervartanian.xyz/aibd/records/AIBD-1148.html (archived at https://doi.org/10.7910/DVN/AADSII, version 7.0)

BibTeX Data Field definitions