AppTek Updates Automatic Speech Recognition, Isometric Neural Machine Translation, and Speaker-Adaptive Dubbing

AppTek, a provider of artificial intelligence, automatic speech recognition, neural machine translation, natural language processing/understanding, and text-to-speech  technologies, this week will showcase its latest advancements in human language technology for the broadcast news and media and entertainment industries.

AppTek's latest suite of speech and language technology solutions ushers in "new realms of efficiencies and cost savings for broadcast media professionals," said Kyle Maddock, senior vice president of sales and marketing at AppTek, in a statement.

AppTek's fully automatic speaker-adaptive dubbing solution can transcribe and translate audio from one source language and present it back in the same voice in the target language while maintaining the time constraints, style, formality, gender, and other context- or domain-specific translations .

AppTek's ASR and machine translation technologies are designed to reduce manual labor and accelerate production timelines for captioning and subtitling workflows using content metadata, such as genre, style, speaker gender, etc., while its Intelligent Line Segmentation technology has been trained via neural networks on the segmentation decisions of professional captioners and subtitlers.

AppTek's text-to-speech technology converts written text into spoken words using either pre-built or customized voices. The technology can be used in a wide range of applications, such as accessibility for disabled users for critical text-based news crawls, such as to announce school closings.

AppTek's voice conversion technology transforms one person's voice into another person's voice and can be used for a variety of purposes, such as creating virtual voice actors where adult actors can mimic the voices of child actors or adding personalized voice-over to videos or advertisements.

AppTek's language identification technology determines the language of a given text or audio input which can be used to manage unknown subtitle or audio files or identify multiple languages within a given file to segment for other automatic processes, such as automatic speech recognition or machine translation.

And finally, AppTek's OmniCaption 300 captioning appliance offers live automated captions for broadcasters through its stand-alone server installed with the latest advancements in ASR technology that resides on premises and delivers real-time fully automated closed captions.

SpeechTek Covers
for qualified subscribers
Subscribe Now Current Issue Past Issues