Data
OOONA and AudioShake Join Forces to Increase ASR Transcription Accuracy
Story Highlights
The partnership will make AudioShake’s speech clean-up technology available within OOONA’s Integrated platform. ASR technology has opened up captioning services to a broad range of content but transcription accuracy can still fall short when additional background noise or music is present.
AudioShake’s patented technology cleanly separates dialogue and music from a video or audio file, allowing ASR, captioning and dubbing services to benefit from cleaner input audio.
Widely used across the music and entertainment industries, AudioShake’s audio separation technologies have been shown to improve transcription accuracy by more than 20% and are particularly helpful in cases where recordings have poor quality, low fidelity, or considerable background noise.
Through seamless integration into the OOONA Create and OOONA Transcribe tools as well as the OOONA Integrated platform, customers will have the option to clean their audio using AudioShake before running it through ASR and captioning technologies to create more accurate automatic captions.
“I am certain the AudioShake cleanup tool will help our users who frequently have to deal with noisy audio,” says Wayne Garb, OOONA co-founder and CEO. “We aim to provide our customers with the option to use any tool that facilitates their production work. AudioShake is the latest in the series of API integrations we are investing in to ensure the OOONA ecosystem truly has it all.”
“AudioShake’s audio separation technologies are trusted by a wide range of broadcasters, music labels, content analysers and entertainment professionals to help improve their transcription, dubbing and analysis tasks,” adds Jessica Powell, AudioShake co-founder and CEO. “We’re thrilled to integrate on the OOONA platform, making it easy for their users to use AudioShake as part of their workflow.”
