As another NAB SHOW approaches, VoiceInteraction prepares to unveil the latest developments of its solutions for the Broadcasting, Media & Entertainment Industries, with special emphasis on AUDIMUS.MEDIA, a Fully-Automatic System for Live Subtitling of Audiovisual Contents.

NAB SHOW 2016 will be held in Las Vegas, NV, April 18-21, 2016. Join us at booth SU1621, South Hall (Upper).

The community’s increasing awareness about the need for policies to ensure everyone equal opportunities and access to information and knowledge has led to the creation of rules imposing requirements on TV broadcasters to provide their contents in alternative ways, such as sign language and/or subtitling. Because subtitlingg proved to be useful in a broader range of circumstances — e.g. subtitles have been explored in language acquisition; subtitling enables people to watch (and understand) TV programmes in noisy (shopping centers) or quiet (hospitals) public places –, broadcasters have turned attention to this alternative content description as a means to reach a wider audience. Subtitling, though, is costly and (human) resource-intensive. Automatic tools producing high-quality results at affordable costs have, thus, been researched for years. Before fully automated approaches come into existence, solutions like re-speaking — in which an individual (re-speaker) listens to the audio track and dictates (verbatim or a summary of) the content to a speech-to-text conversion system adapted to his/her voice characteristics — was the most cost-effective subtitling method.

VoiceInteraction – Speech Processing Technologies, S.A. pioneered the use of speaker-independent voice recognition technology in real-time, live subtitling of broadcast contents through AUDIMUS.MEDIA, a fully automatic subtitling system that, in addition to transcribing the spoken utterances, segments them according to the speaker holding the turn. The system builds on the capability of VoiceInteraction‘s speech transcription technology to operate faster than real time (i.e. transcribes speech faster than playback time) with speaker-independent models and very large vocabularies.

This year’s event will be used for the global launch of its screenplay time-coding solution, built to allow Media & Entertainment professionals to go a step further in automating the building of post-production scripts. Apart from that, VoiceInteraction will showcase its Media Monitoring System, with special emphasis on the Broadcast Edition of it, devoted to accommodate the specific needs of TV broadcasters and Government departments (regulatory agencies). It will be certainly worthwhile attending our demos of the latest version of AUDIMUS.MEDIA — a fully-automatic subtitling system that, besides transcribing the spoken utterances, segments them according to the speaker holding the turn — building on the integration of deep-learning techniques in our speech processing technologies to optimize the performance of acoustic models derived from the ever-growing speech repositories.

In addition to watching the demos available at our booth, our visitors will have the opportunity to gain some insight into a broader range of proven speech processing solutions, such as Speech Transcription Systems for court, medical, parliament and council proceedings, TTS and ASR Engines for IVRs and Speech Analytics in Call Centres, and Embodied Conversational Agents for multi-modal applications. We are looking forward to receiving your visit at our booth SU1621 (South Hall Upper 1621, Brazil’s Pavilion). If you wish to schedule a meeting during the event for more thorough discussions with Prof. João Neto, CEO of VoiceInteraction, please, send us a Meeting Request to the email nabshow2016@voiceinteraction.tv

NAB SHOW is the world’s biggest annual conference and exhibition in the area of production, management and delivery of audiovisual contents. With more than 98,000 attendees from 150 countries and 1,700+ exhibitors, the event will be held at the Convention Center of Las Vegas, from April 18 to April 21, 2016, and is organized by National Association of Broadcasters.

VoiceInteraction was created in 2008 as a technological spin-off from the INESC-ID, Lisbon, providing cutting-edge speech synthesis technology for building customized voices to accommodate the branding needs of its clients and speaker-independent speech recognition technology that paved the way for the development of a fully-automatic live subtitlingg system for the broadcasting and media production industries, in addition to broadcast monitoring solutions devoted to automate workflows of clipping service providers.