enCaption4 captions mostly meet Canada's live accuracy standard

The broadcaster's certified evaluator scored its automatic ENCO enCaption4 live news captions from 97.65 to 98.61 across 48 samples in 2023-2024, mostly at or above the CRTC's 98.

  • Not rated a person

    The evaluator scored the captions near the standard for one season, but the report gives no earlier figures and no outcome for viewers beyond the absence of complaints.

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

Status
Reported benefit.
Evidence

foundstudiedreportedclaimed

Only the evaluators support the benefit.

The system’s part
Not isolated. The evaluator scored captions that enCaption4 produced with no captioner at broadcast time, but the report compares them with neither human captions nor earlier results. Staff maintain the system's local lexicon. ENCO says that the enCaption4 engine uses machine learning to build a deep neural network approach to voice recognition.
Not yet checked
LimitsCosts and harmsLearns from dataLater outcome

Download data Cite Suggest a correction

Benefit type
Improved Accessibility
System
ENCO enCaption4 automated live captioning
Made by
ENCO Systems
Used by
Thunder Bay Electronics Limited (Dougall Media), for CKPR-DT and CHFD-DT
Where
Thunder Bay, Ontario, 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. Evaluation report, by an evaluator that the makers or users commissioned.

    Thunder Bay Electronics Limited (Dougall Media), CKPR-DT and CHFD-DT. Annual closed captioning report for the 2023/2024 broadcast season, filed with the CRTC under Broadcasting Regulatory Policy CRTC 2019-308, 29 November 2024, with NER scores by a certified NER evaluator that the broadcaster engaged. Archived copy of https://crtc.gc.ca/eng/BCASTING/ann_rep/tbayelec_cc2024.pdf.

    Occasionally our NER evaluations score less than 98. The primary cause is punctuation and speaker change detection issues.
    In early 2019, we implemented ENCO's enCaption4 amid positive industry reviews and successful in-house testing.
    During the 2023/2024 broadcast season, we did not receive any complaints or concerns from viewers.

  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. Press release, by the makers. Context or contrary evidence.

    ENCO Systems. ENCO to Unveil Automated Closed Captioning Breakthroughs at NAB Show New York. Press release, Southfield, Michigan, 5 October 2017 (enco.com). Accessed 1 November 2026.

    enCaption4's new speech-to-text engine takes this accuracy to an unprecedented new level, leveraging breakthroughs in machine learning technology to develop a deep neural network approach to voice recognition.

Details

AI system

Reported configuration

EnCaption4

Workflow

ENCO's enCaption4 captioned live programs automatically, with a redundant system in case the main one failed. Master control operators ran the system and monitored its output throughout the day. Staff maintained the system's local lexicon of new, unusual or local words. The broadcaster sent its NER evaluations to ENCO to guide software updates.

Follow-up

Conditions for replication

Live English-language captions must score at least 98 under the Canadian NER guidelines, as calculated by certified evaluators. Punctuation and speaker-change detection must improve for scores to stay at or above 98.

Entry details

Sector

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

Purpose

ENCO built enCaption4 to caption live and pre-recorded programs automatically in near real time.

30 more questions not yet checked

model, 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). enCaption4 captions mostly meet Canada's live accuracy standard (AIBD-1149). Artificial Intelligence Benefits Database, edition of 1 November 2026. https://petervartanian.xyz/aibd/records/AIBD-1149.html (archived at https://doi.org/10.7910/DVN/AADSII, version 7.0)

BibTeX Data Field definitions