Internet resources: Automatic Searchable Speech Transcripts unveiled

The French search engine Exalead claims that it's cracked one of the biggest challenges of search, making audio- and video searchable. A case in point is the Website of France's President, which is using Voxalead, developed by Exalead, to automatically transcribe online video and audio files and converts them into text. Now, Voxalead makes it possible to search all the videos of President Nicolas Sarkozy stored on the site for speeches and press conferences in which he used a particular word or phrase, jumping straight to the spot in the video where he utters the word. The transcripts can be overlaid on the videos as subtitles.

Google's YouTube also offers searchable transcripts of some of its videos, and it too uses those transcripts for subtitling. The technology of voice recognition, which provided the opportunity to convert human speech into a printed text, was borrowed from Google Voice service. The service initially is supporting just English speech, however in future YouTube is going to add subtitles in 50 languages.     

 Unlike YouTube, Voxalead supports recognition of speech in English, French, Chinese, Arabic, Spanish and Russian.

The advantages of automatic subtitles are evident. Thus, transcripts will be useful for hearing-impaired users. Subtitles will help to get the message of video clips in noisy places — for instance, at railway stations and airports. They can be used to facilitate foreign language learning, and simplify understanding of the foreign speech.