To address that, Google announced Wednesday that it has launched audio indexing in Google Labs.
Recently, audio segmentation has attracted research interest because of its usefulness in several applications like audio indexing and retrieval, subtitling, monitoring of acoustic scenes, etc.
Pittman's talking about previous Google Labs products, Streetview, Picasa facial recognition, audio indexing (search for spoken words in video) and Google translate.
Other new features in this release include Spanish support for Azure's speech-to-text audio indexing service, as well as certification from the Content Delivery Security Association for content owners and delivery services that need to be able to prove that their content is stored securely and can't be easily pirated.
The company claims it's able to index audio files in less than half the time of a human transcriber, and costs 75 cents per hour of audio versus the 75 cents per minute charged by human transcription services.
According to the company, GAudi is only in beta at this point and during that time, it will only index audio and video from political sources.
The media center indexes audio, video and picture files on your hard drive for consumption on the Openride video player.
The company was founded by Sumner Murphy, who has startup and engineering experience, but nothing that seems to be specific to solving the challenge of indexing audio in particular.
We define xν,τas the magnitude spectrum of the audio data with frequency index ν and time frame index τ, where ν ∈ {1, 2,..., F} and τ ∈ {1, 2,..., T}.
where i denotes the index of audio frame, and P i and P ^ i are the power spectra of the original SWB audio signals and the extended audio signals, respectively.
