Indexing Sound Files on Search Engines that Can’t Hear Them

Référence bibliographique:

SLAWSKI, Bill. Indexing Sound Files on Search Engines that Can’t Hear Them. Creative Flow, May 27th, 2004. URL: http://blog.cre8asite.net/archives/125

Text:

"What do you do if most of the content your company creates is in audio or video format, and you want to include it on the web, and make it so that people can find it? And the content is news, which relies upon timely delivery?

In the case of National Public Radio (NPR), the answer was to put the audio files online, and also offer transcriptions of them. Since NPR started doing that a few weeks ago, they’ve noticed a substantial increase in traffic to their site for topical subjects from the search engines.

One of the things I like about this practice is that people with hearing disabilities are now able to access stories that they couldn’t hear on the radio. What a great result.

The transcription is presently done by speech recognition technology to get stories online very quickly after they are broadcast on the radio. It’s likely that humans will take over from the software presently used, which sometimes garbles results.

If at some point, the search engines become capable of indexing audio, I hope that sites providing transcripts continue to do so. It’s great to see such a great improvement in accessibility, even if it is done inadvertently."

Dublin Core Metadata:

Title: Indexing Sound Files on Search Engines that Can’t Hear Them
Creator: Bill SLAWSKI
Subject: Audio file / audio format / video format / indexing audio / National public radio / recognition / speech recognition.
Description: "What do you do if most of the content your company creates is in audio or video format, and you want to include it on the web, and make it so that people can find it? And the content is news, which relies upon timely delivery?"
Contributor: -
Date: 2004/05/27
Type: Article
Identifier: http://blog.cre8asite.net/archives/125
Source: Creative Flow
Language: En
Coverage: World
Rights: -

Audio and Sound Information

This site was created by an old student of GIDO (Gestion de l'Information et du Document dans les Organisations) at the IUT Michel de Montaigne (France, Bordeaux) in 2006.
It gives information on the processing of audio documents thanks to web sites links. It is composed to two parts, the first on the sound information and the second on the processing on the audio documents.
It contents nine links, you can visited the Assocation for recorded sound collections (ARSC), the Association des détenteurs de documents audiovisuels et sonores (AFAS), or the International Association of Sound and Audiovisual Archives (IASA) for example.

Clic on the link to visit the site Audio and Sound Information: http://www.iut.u-bordeaux3.fr/doc/sitos2006/Info%20son/Index.htm

Speech and language technologies for audio indexing and retrieval

Bibliographic reference

MAKHOUL, John et al / Speech and language technologies for audio indexing and retrieval. Proceedings of the IEEE, Vol. 88, N° 8. AUGUST 2000. URL: http://www.bbn.com/docs/whitepapers/Audio-Indexing-Retrieval.pdf

Text

URL: http://www.bbn.com/docs/whitepapers/Audio-Indexing-Retrieval.pdf

Dublin Core Metadata:

Title: Speech and language technologies for audio indexing and retrieval
Creator: John MAKHOUL
Subject: Audio indexing, information extraction, information retrieval, speech recognition, segmentation, classification.
Description: This paper explain how to extract audio information. It proposes figures of the Rough'n Ready System witch it is possible to indexing and retrieval sounds. It also talks about the speech recognition and the segmentation.
Contributor: -
Date: August 2000
Type: Pdf
Identifier: URL: http://www.bbn.com/docs/whitepapers/Audio-Indexing-Retrieval.pdf
Source: Proceedings of the IEEE
Language: En
Coverage: World
Rights: IEEE

An Online Audio Indexing System

Bibliographic reference:

AJMERA, Jitendra. McCOWAN, Iain. BOURLARD, Herve / An Online Audio Indexing System. IDIAP, Switzerland. 2002. URL: ftp://ftp.idiap.ch/pub/reports/2003/rr03-39b.pdf

Text:

Sumary: "This paper presents overview of an online audio indexing system which creates a searchable index of speech content embedded in digitized audio files. This system is based on our recently proposed offline audio segmentation techniques. As the data arrives continuously, the system first finds boundaries of the acoustically homogenous segments. Next, each of these segments is classified as speech, music or \it mixture classes, where mixtures are defined as regions where speech and other non-speech sounds are present simultaneously and noticeably. The speech segments are then clustered together to provide consistent speaker labels. The speech and mixture segments are converted to text via an ASR system. The resulting words are time-stamped together with other metadata information (speaker identity, speech confidence score) in an XML file to rapidly identify and access target segments. In this paper, we analyze the performance at each stage of this audio indexing system and also compare it with the performance of the corresponding offline modules."

URL: ftp://ftp.idiap.ch/pub/reports/2003/rr03-39b.pdf

Dublin Core Metadata:

Title: An Online Audio Indexing System
Creator: AJMERA Jitendra, McCOWAN Iain, BOURLARD Herve
Subject: audio files, audio indexing, automatic speech recognition, speaker clustering.
Description: "This paper presents an overview of an online audio indexing systemwhitch creates a searchable index of speech content embedded in digitized audio files."
Contributor: -
Date: 2004
Type: Paper
Format: Pdf
Identifier:URL: ftp://ftp.idiap.ch/pub/reports/2003/rr03-39b.pdf
Source: IDIAP Research Institute
Language: En
Coverage: World
Rights: IDIAP

Glossary English / French

Automatic sound indexing
“These methods allow the system to automatically organize new sounds introduced by the user, by analyzing their content in relation to predefined categories."
Name: IRCAM Centre Pompidou.
URL: http://www.ircam.fr/307.html?&L=1&tx_ircam_pi4[showUid]=15&cH
ash=72de9812b5

Indexation automatique des sons
“ Méthode permettant au système de ranger automatiquement les nouveaux sons introduits par l’utilisateur à partir d’une analyse de leur contenu selon des catégories qu’il aura prédéfinies.»
Nom : IRCAM Centre Pompidou.
URL : http://www.ircam.fr/307.html?&L=0&tx_ircam_pi4[showUid]=15&cH
ash=72de9812b5


Cataloging
"The compilation and maintenance of primary information by systematically describing objects in the collection, and the arranging of this information into an object catalog record."
Name: International Guidelines for Museum Object Information: The CIDOC Information Categories.
URL: http://www.willpowerinfo.myby.co.uk/cidoc/guide/guideglo.htm

Catalogage
"Consiste à analyser le document en tant que support."
Nom : Methodoc.
URL : http://www.scd.univ-lille3.fr/methodoc/cours/typedocument/catal
ogage.htm


Indexing
"The process of converting a collection of data into a database suitable for easy search and retrieval."
Name: Virtech E-solution-SEO: E-Solutions and Web Development for Today's Internet
URL: http://www.virtechseo.com/seoglossary.htm

Indexation
"Consiste à analyser le document pour les informations qu'il contient."
Nom : Methodoc.
URL : http://www.scd.univ-lille3.fr/methodoc/cours/typedocument/
indexation.htm


Record
"A group of fields relating to a particular object or transaction."
Name: International Guidelines for Museum Object Information: The CIDOC Information Categories.
URL: http://www.willpowerinfo.myby.co.uk/cidoc/guide/guideglo.htm

Enregistrement
"Fait de recueillir et de conserver (une donnée) au moyen d'appareils appropriés."
Nom : TLFI : Trésor de la langue française informatisé.
URL: http://atilf.atilf.fr/dendien/scripts/tlfiv5/saveregass.exe?43;s=2841
038385;r=2;;


Segmentation
"The process by which speech signals are divided into phonemes, syllables or words."
Name: Keith Yates Design Group.
URL: http://www.keithyates.com/index.html

Segmentation
"Consiste à détecter les variations brusques du signal, à détecter les transitions entre deux zones stables successives."
Nom : Thèse : Segmentation et indexation des sons.
URL: http://stephanerossignol.ifrance.com/


Sound recording
"The fixation of a series of musical, spoken or other sounds."
Name: The sound of American music company.
URL: http://www.americanmusicco.com/license/helpfulHints.asp

Enregistrement sonore
"Opération qui consiste à garder la trace d'un son de façon durable sur un support analogique comme la bande magnétique ou le disque vinyle, ou sur un support numérique comme le disque compact, en vue de pouvoir le diffuser au plus proche de l'identique et éventuellement le modifier (le traiter)."
Nom : Techno-science.net
URL: http://www.techno-science.net/?onglet=glossaire&definition=1256