Virtual meetings are cost- effective, save time and improve productivity. These can be transcribed with the help of digital transcription services.
As technology advances, the process of organizing conferences and the equipment used for them are also changing. The latest trend in making conference calls is virtual reality. With advanced technology and the internet, meetings can be virtual. Virtual meeting or online meeting is an event or series of events where participants join in from multiple locations by teleconference or video conference. Virtual meetings are cost- effective, save time and improve productivity. These virtual meetings can be transcribed with the help of digital transcription services.
Virtual reality is the new solution for making uninterrupted conference calls. Video calls provide a layer of intimacy, allowing face-to-face communication but that is not always enough. Voice and eye tracking technology gives a sense of eye contact and facial expression and virtual reality adds an interpersonal connection that video or phone cannot do. Today with the outbreak of COVID 19, virtual meetings have become very useful for businesses to connect with their employees and carry out business operations seamlessly.
Incoming stream of source words
Virtual meetings are now focusing more on integrating language technology, such as machine translation (MT) and automatic transcription. According to Gartner’s Magic Quadrant for Meeting Solutions, published on September 5, 2019, 80% of the vendors they profiled have some version of meeting transcription software that are based on natural language processing (NLP) technology with AI.
Google is making efforts to integrate natural language processing to compete with challengers like Zoom, Microsoft, Cisco, LogMeIn etc. In 2019, Google Meet started offering live captions and now Google researchers are focusing on solving the simultaneous translation problem that is important for providing live translated captions for audio or video.
In a paper published in mid-April 2020, Google researchers Naveen Arivazhagan, Colin Cherry, Wolfgang Macherey, and George Foster compared two major approaches to simultaneous translation, streaming and re-translation. They aim at improving machine translation (MT) to translate an incoming stream of source words with as low latency as possible. Till now, the dominant approach has been streaming and along with streaming, translated text cannot be changed once it has appeared on screen. Re-translation, by contrast, allows modifications to the translated text even after it is displayed on screen. Google tested which approach produced better translations (quality) and which led to a shorter delay in the translated text appearing on screen and found that re-translation performed better than streaming based on both quality and latency.
Re – translation is a strong baseline
The researchers consider re-translation as a strong baseline for future research and simultaneous translation and further research could find a lower cost solution that preserves the flexibility of re- translation. Many providers like Zoom provide transcription after the event based on recorded audio rather than live caption during the event. Cisco (Webex) provides real-time transcription and closed captioning during meeting and recording, and transcripts after the meeting.
Although AI transcription solution is well implemented, real-time transcription and interpretation is not resolved yet. With Google planning further research into simultaneous translation, it may not be long before it is deployed in Google Meet in the form of live translated captions.
Technological advancements are transforming the conventional method of conducting meetings by providing real-time transcription. But it is important to remember that machines are prone to error because these tools are all programmed and sometimes may not be able to decipher important information. Therefore, a digital transcription service is still essential to ensure utmost accuracy.