Microsoft Commercial and Professional Services Germany Company newsroom

DLG (German Agricultural Society)

DLG needed a way to turn live trade-fair presentations into written, barrier-free, multilingual content so international attendees and people with hearing impairments could follow sessions without relying on traditional simultaneous interpreters.

five stages in parallel
more than 100 languages

Reported impact

Business outcome

DLG expanded the reach of its trade fairs with multilingual, barrier-free access to presentations, created additional value for attendees and partners, and reduced the cost of hiring simultaneous translators.

  • Cost Reduction
  • Customer Experience

Solution

DLG deployed transcribbyAI from Deutsche Telekom MMS as a browser-based AI simultaneous interpretation application for its trade fairs. Organizers run the application on a computer that receives the live event audio stream; a microphone connects through a standard audio cable, or a recorded audio file can be played in as the source. transcribbyAI uses Microsoft Azure AI language models to perform real-time speech recognition, speech synthesis, and translation, automatically detecting the source language and translating output into more than 100 languages. During pauses it corrects capitalization and punctuation, masks inappropriate expressions with symbols, and distinguishes speakers by voice color. The resulting text is delivered to large stage screens and to mobile devices through QR-code access. The source does not name a dedicated storage product, but it does state that transcripts can be exported for further processing. The solution was operated on German servers with certified IT security and GDPR-compliant hosting, and Telekom MMS ran it across five stages in parallel at Agritechnica.

Data flow

A presentation audio stream reaches a browser-based transcribbyAI session from a connected microphone or from a played-back audio file. transcribbyAI uses Microsoft Azure language models for real-time recognition and translation, then returns corrected subtitles and multilingual text to stage screens or QR-code mobile views, with transcript export available for further processing.

Solution architecture

2 components · 2 layers
  1. Compute
    • Microsoft Azure Provides the AI language models that power speech recognition, speech synthesis, and language translation for the live interpretation workflow.
  2. Serving
    • transcribbyAI Browser-based application used by DLG to ingest event audio, generate live transcripts and translations, and deliver accessible text to screens and mobile viewers.

Architecture clues

  • Certified IT security
  • Operated in compliance with the GDPR on German servers
  • Telekom MMS provided the application on five stages in parallel at Agritechnica
  • The number of listeners can be flexibly adjusted
  • Transcripts can be exported for further processing

Evidence from the source

"DLG saves costs by eliminating the need for simultaneous translators."
"Telekom MMS ... provided the required application on five stages in parallel."
"The tool is based on the latest AI language models from Microsoft Azure, which enable speech recognition, speech synthesis and language translation."
"the DLG was looking for a way to simultaneously transmit presentations in written form (speech to text). In addition, the text output for a large stage monitor had to be optimized to be barrier-free and multilingual."
"transcribbyAI automatically recognizes the source language and can translate into more than 100 languages individually for each user."
Transparency Evidence & methodology 75/100 reference value · 95% confidence · 2 sources

Review how this reference was scored and trace each normalized claim back to its documented source.

01

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value75/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth25/25
    Rewards named components, data flow, integrations, and architecture detail.
  • Outcome specificity20/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact0/25
    0 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence95%
  • Source authority25/25
    The deployment is described by the adopting organization or a government source.
  • Claim traceability23/25
    11 of 12 key fields link to a named source.
  • Direct evidence20/20
    5 direct source quotes retained.
  • Date provenance10/10
    The publication date comes from the source page or publisher.
  • Source transparency9/10
    2 source references document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity8/10
    Rewards source-backed components, data flow, quantified impact, and a specific outcome.
02

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

  1. DLG (German Agricultural Society)

    DLG (German Agricultural Society) customer story

    First-party
    https://www.telekom.com/en/newsroom/latest-updates/media-information/2024/8/inclusion-and-innovation-ai-translation-at-dlg-trade-fairs
    Source type
    Customer-published story
    Published
    Aug 15, 2024
    Supports
    • Customer
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • technical area
    • use case category
    • Business outcome
    • outcome category
    • Metrics
    • Architecture
    • evidence quotes
    • Publication date
  2. German Pavilion

    German Agricultural Society - DLG e.V.

    Independent secondary
    https://agritech.german-pavilion.com/en/sites/contact/2227

    The profile states 'DLG employs 200 full-time staff' and identifies the organization as based in Germany.

    Source type
    Structured organization profile
    Supports
    • Company size

Date evidence

  • Published on source page Aug 15, 2024 · Deutsche Telekom AG · First-party
    Open date source
Not separately sourced Industry, Region. Treat these normalized attributes as lower-confidence until a dedicated source is added.