Gareth Long
Gareth Long, New Haven, CT, 2006, English
Fiction; Nonfiction, Graphic Design

From the Publisher. A book generated by processing the Audiobook version of Don Quixote through speech recognition software. After training the speech recognition software to recognize the voice of George Guidall – the narrator of the audiobook, the recording was played to the computer. The resultant text was reformatted to once again be a book. 


This book extends the self-reflexive, tale-telling nature of Don Quixote even further by using a text generated though the playback of an audio version to a dictating software program. The artist labored to train the program to recognize the book-on-tape's voice, but the software still tripped over silences and pauses. The word Quixote also proved elusive for the computer's comprehension as the name doesn't appear anywhere in this version.

This book was generated by processing the Audiobook version of Don Quixote (Edith Grossman's 2003 translation) through speech recognition software. For the software to work it must first be trained using a very particular script to understand an individual's voice – in this instance, the narrator of the audiobook, George Guidall. To accomplish this, the words in the training script were found within the Grossman book version. These words were then located on the corresponding audio CD, removed from their contexts and rearranged as if George Guidall was speaking the training script. Certain words that were not found in the novel ('module', as an example, was not a common word in 17th century Spain) were created by combining words: the first syllable of 'modesty' was put with the word 'jewel' to create the phonetic sounds of 'module'. After the audio files for the training speech were completed, this constructed speech reading was played to the speech recognition software, effectively training the computer to learn the voice of George Guidall. With this in place, the speech recognition software was ready to hear Guidall's reading of Cervantes' book.

The constructed voice of Guidall, however, did not make for a perfect cypher. Often, Guidall used different voices for characters or Guidall ran words together – not necessarily enunciating each word to its fullest, throwing off the accuracy of the software. At other times, words such as 'Don Quixote' were unknown to the software's built-in dictionary and came out differently, in certain instances, as 'Donkey vote.' Further, much of the text reads like a Joycean stream, as the speech recognition software could not decipher the silent punctuation of the audio source. The moments in the text where punctuation does appear are most likely mis-hearings of other words (where 'calm' is heard as 'comma,' for example).

This generated text was then culled and printed as a book, closely resembling the standard paperback edition of the 2003 Grossman translation.

Beyond Don Quixote's obvious canonical importance as the first modern novel, the story itself is about books and reading through plays with meta-narratives, questions of authorship, and the book as an object of fetish. Like the novel, this new version is also preoccupied with these and many other subjects, including the exploration of the differences in reception between the act of both reading and listening.

On 1 book list
Prem Krishnamurthy

I can’t think of a “copy” more fittingly perverse than Gareth Long’s Don Quixote (2006). Long generated this text using speech recognition software, which he trained to identify the Don Quixote audiobook narrator’s voice. He played the subsequent recording into a computer and produced this clever doppelgänger. His “Chapter XVI” begins: “regarding what they fail in the ingenious government in the American debut Castle.”

comments powered by Disqus