What's special about Google Scholar searches

The titles, author lists, and abstracts of papers in the ISCA Online Archive are all on the public web, so they can be searched by a general-purpose search engine such as Google. To restrict a Google search to the ISCA web site, add the term site:isca-speech.org to the search.

Google Scholar is a specialized research literature search engine, which indexes the full text of ISCA papers through an arrangement with ISCA. (On the other hand, general-purpose search engines index a lot of material on the public web which is not in the Google Scholar index or the ISCA Archive. So it's often useful to perform the same search using both Google Scholar and a general-purpose search engine.)

Besides full-text searches, Google Scholar has other useful capabilities. Google Scholar automatically extracts citations from the full text of papers, and it uses this information to provide a "Cited by" list for each paper in the Google Scholar index. This lists the papers that have cited that paper. This is very useful for finding follow-up work, related work and corrections. Google Scholar also provides an automatically generated "Related Articles" list for each paper.

Since the ISCA Archive is largely a volunteer effort, there is sometimes a delay between when a conference or workshop appears in the online ISCA Archive and when the necessary catalog data is created for Google Scholar. (ISCA provides Google Scholar with catalog data in a special format.) And then there may be an additional delay until the Google Scholar index is updated. Thus there can be a long delay before new ISCA events appear in Google Scholar search results. For example, INTERSPEECH 2007 papers were not yet included as of November 2008, except for some papers which were placed online by the authors on non-ISCA web sites. On the other hand it's possible to use regular Google searches if you just want to search titles, author lists, and abstracts. For example, as of November 2008 a regular Google (not Google Scholar) search for "phonology 2007 site:isca-speech.org" (without the quotation marks) returns a long list of INTERSPEECH 2007 papers.

Many papers from 2001 and earlier have been scanned in from paper copies. Google uses optical character recognition (OCR) technology to obtain the full text of those papers. This allows the scanned papers to be covered by the full text search and citation tracking capabilities of Google Scholar. The OCR technology is not 100% accurate but it does a fairly good job. Please let us know if you come across any scanned papers for which OCR is not being used.