Organization of American States
View OAS case study video:
The Organization of American States is the world’s oldest regional organization, dating back to the First International Conference of American States, held in Washington, D.C., from October 1889 to April 1890. That meeting approved the establishment of the International Union of American Republics, and the stage was set for the weaving of a web of provisions and institutions that came to be known as the inter-American system, the oldest international institutional system.
Today, the OAS brings together all 35 independent states of the Americas and constitutes the main political, juridical, and social governmental forum in the Hemisphere. In addition, it has granted permanent observer status to 69 states, as well as to the European Union (EU). The Organization uses a four-pronged approach to effectively implement its essential purposes, based on its main pillars: democracy, human rights, security, and development.
Manual and Time-Consuming Transcription
The GS/OAS is mandated to keep verbatim minutes of the meetings of some of its governing bodies These meetings are manually transcribed in order to maximize their value for researchers, to preserve its historical records and to facilitate its Member States access to the content and also to reach out to diverse audiences.
This transcription process is manual, time-consuming and requires personnel to spend up to 20 hours to transcribe a single hour of recorded content. A typical four-hour video, therefore, is taking up to 80 hours of work in order to complete the corresponding “verbatim minute”, hence generating a huge backlog of transcriptions not allowing the GS/OAS to have these minutes in a timely manner.
AI driven media asset management
In order to streamline, automate, and accelerate the translation process, the OAS has turned to Primestream’s advanced media asset management (MAM) solution platform, leveraging powerful artificial intelligence (AI) tools and technologies. Based on Primestream’s cloud-based Xchange™ MAM platform, the new system will deliver, significant new efficiencies, cost savings, and enhanced service to GS/OAS Member States.
MAM transcribes audio content automatically using AI capabilities such as voice recognition, identifies the speaker with facial recognition, and automatic metadata tagging. Next, the system outputs the transcription in multiple languages for rapid delivery to delegates from the 35 OAS Member States. The tagged transcriptions are uploaded to Xchange’s centralized, cloud-based storage to make the media content searchable and give GSA/OAS personnel fast and easy access to all media assets.
At the OAS, media users and metadata organizers are tasked with creating metadata descriptions and uploading the completed recordings of the events to the Primestream Xchange™ environment. There, the content is associated with the descriptive metadata relating to the event, such as date, name, location, and agenda, and stored in a “meetings” placeholder.
Next, MAM automatically creates a proxy and sends all uploaded clips to the Microsoft ® Azure Video Indexer platform for AI analysis of the content. At this stage, the facial recognition module within the Xchange Elastic Data Viewer™ comes into play. By creating an index of faces appearing in each video, the platform is able to catalog and segment the content by participant. With indexed markers pointing to specific speakers who take part in these multinational meetings, the Elastic Data Viewer makes it easier for GS/OAS personnel to access content based on meeting participants.
CPMS User: The CPMS User (Conference Proceedings Management System) is tasked with creating the initial metadata descriptions and uploading the completed recordings of the events into the system. The first task of the CPMS User is to create a “meeting” placeholder in the MAM to which incoming uploaded clips will be attached. These placeholders are categorized as meetings in the OAS workflow. The “meetings” contain basic descriptive metadata such as Date, Name, Location, and Agenda.
OAS meetings are recorded and, when finalized, it is the responsibility of the CPMS User to upload the recording into MAM utilizing a customized UX designed specifically for pushing content into it. In uploading the clip the CPMS User will associate the recording with the intended pre-created “meeting” placeholder by searching and or selecting from a list. This user will receive an email notification that the upload was completed successfully.
The OAS workflow has an intelligent process, configured to automatically create a proxy and send all uploaded clips to the Azure Video Indexer platform for AI analysis of the content. The uploaded clips will be analyzed for facial recognition and audio transcription of the four languages used in OAS meetings: English, French, Spanish, and Portuguese.
Editor User: Looks at the clip in Xchange after the pass through the Primestream Video Indexer. The editor sees all tracks relating to facial recognition and language transcription. It is the job of the editor to make a first pass of the analyzed content, confirm the correct meeting has been uploaded and add any corrections or additions to the facial recognition done by the AI. Changes and or additions to faces will assist the AI engine in identifying the same faces in the future.
Transcriptor User: Reviews and corrects the transcripts from the audio of the analyzed clips. Approver User: Signs off on the final version of the corrected transcripts and other analyzed metadata; Additionally, can download a file as an srt, text, or csv format of the finalized transcripts to create the Official Document in Word format to then upload and attach the file to the meeting video project.
The Approvers are presented with the same landing UX as the Editors for browsing and selecting the recording and reviewing the analysis done by the AI platform.
Inquirer User: Search and visualize of all material available and watermark the content according to certain classification rules . This user can search by name, date, location, among others and can see the closed captions available in multiple languages. Additionally, this user has access to the Official Document in Word format that has the general information and links of OAS meetings published.
The uploaded clips are then transcribed in the four official languages used in OAS meetings – English, French, Spanish, and Portuguese. When the AI engine completes its analysis of the uploaded content, an email is automatically generated to notify the other user groups that there is a clip ready to be reviewed
OAS editors then review each clip using the Xchange Elastic Data Viewer, which offers a timeline for displaying the data from the AI engine analysis. The editor reviews the analyzed content to confirm the correct meeting has been uploaded and to add any corrections or additions to the facial recognition done by the AI analysis. Changes and additions to faces help the AI engine “learn” to identify the same faces in the future.
Once the editor’s job is complete, a transcriptor reviews and corrects the transcript from the audio of the analyzed content. Finally, an approver gives final signoff that the corrected transcripts and confirms other analyzed metadata are accurate. It’s the approver’s job to create the “Official Document” in Word format and then upload and attach it to the associated meeting video.
With the Official Document uploaded, end users are now able to search on the content by name, date, and location and access the “Official Document” of the meeting with associated video and audio assets.
The OAS’ automated, AI-driven transcription process based on Primestream Xchange™ is a major improvement over the previous manual process, which could take up to 30 days to accomplish the same tasks. Now, instead of the 80-hour turnaround to produce an Official Verbatim Document for a four-hour video, the multilanguage transcription automation of Xchange is able to process the same video in eight hours – a 90% time savings.
By accelerating cataloging and transcription delivery, the GS/OAS is now be able to serve its Member States in a way that would not be possible without the adoption of AI and the dynamic media asset management capabilities of Primestream. With the Xchange platform deployed in a cloud-based architecture, the GS/OAS is able to extend access easily to its video content and related documentation to its offices across the Americas.