Open main menu

Changes

Solipsist Development

2,040 bytes added, 20:16, 12 April 2011
→‎Proposal
==Proposal- Solipsist ==
Ultimately, I decided it would be good to use this project to begin to explore the project I intend to work on next quarter. I have been working with voice recognition technologies and Mel Bochner's text 'Serial Art, Systems, Solipsism', developing a device for performance and exchange between human and computer. The device consists of a microphone, Speech To Text speech recognition system, software, and a receipt printer. The format of the conversation is an dialog between human voice and printed receipts in text--the system transcribes (and validates) whatever what it hears only in terms of the words it knows. As is characteristic of voice recognition, face recognition, and other types kinds of machine perception that operate within explicitly defined or statistically trained spaces of "machine perception", this truly is a solipsistic system (', "denying the existence of anything outside the confines of it's its own mind'" (Bochner, 1967). The challenge for me next term This character of the solipsist is one Mel Bochner evoked to describe the autonomy and denial of external reference in minimalist sculpture of the 1960s, but which I find particularly appropriate to describe current "smart" technologies--ultimately the agency of the system still comes down to develop whatever agency the sound component programmers have embedded in it, a sort of ventriloquism. This idea of a closed, narrowly parameterized space of perception in the machine is an interesting model for (and contrast to) issues of language, vocabulary, and free expression in humans--an exploration I intend to pursue through this piece as performance/installationproject.
So, for There are multiple challenges in developing this project the samples I used were recordings of myself reciting the text of the Bochner text piece as I (or another) would when interacting with the a performance/installation. The composition first and most pragmatic is broken into two types of material--actual words recited, and the pauses, gaps, and inhalations of breath between those wordsget a baseline speech recognition system working. My desire with I have implemented this in the fall using the piece was to emphasize these preSphinx- 4 speech recognition library in Processing and non-verbal utterances (the physical mechanics of breath Java. I have also acquired a receipt printer, ribbon, and voice) while erasingpaper, obfuscating or overwriting the spoken textand can control its printing behavior through a serial interface. While I think I produced some interesting material Details are in the recordings of the silences (especially the first [[#Code | Code]] section of the piece) I am dissatisfied with what I accomplished my use of the spoken-word part of the text. What I would like to accomplish This is a kind the "proof of redaction (similar to redacted text in classified documets) where knowledge some subterranean or obscured content is still clear, but it is impossible to decipher or extractconcept". More on that later I suppose... Well, enough of this, it's time to listen to your pieces!
The development of roles for two characters in this piece--the system and the participant--is necessary to create the kind of encounter I am starting have in mind. On the one hand, I would like this quarter with functional project to investigate the strengths and limitations of the speech-recognition technology through viewer interaction, and on the other hand I would like to create a psychological investigation which highlights our human propensity to project psychology onto inanimate things and to attribute intention to them. Explicit attention in constructing the roles of both performers (human and machine) and in framing the situation will tease out some of the interesting ideas in both of these domains.  Finally, I need to address sonic properties of the piece and its time course as a composition. The voice of the viewer as they speak into the microphone is one sound source in the system, and the receipt printer control code implemented in Processing has a very assertive (and Javaretro) dot-matrix-so ey sound as it prints out text and cuts rolls of paper. I have already demonstrated technical feasibilityneed to make some decisions about how to use the sounds of the speaker and the printer over the course of the piece. Details Also, will I add in additional sound sources such as more printers, pre-recorded voices, voices of past participants, or processed sounds? There are in additional possibilities here for rhythmic exchanges between the percussive sound of the printer and the speaker, for long pauses, silences, and repetitions. Additionally, I need to establish some overall arc for the piece--does an encounter with the system travel through to one pre-ordained conclusion? Are there multiple branching possibilities that change depending on what the viewer says and how they respond to the printouts? Finally there is a relationship to be explored between speech as text and speech as sound--a parallel to the [[#Code | Code]] sectionroles of printing as text and printing as sound. The fundamental distinctions between text, sound, and speech as kinds of communication and expression can be ripe territory for exploration. I suspect that these conceptual and compositional questions will occupy most of my time this quarter and comprise the bulk of the work that I need to do. The most obvious technical challenges for I foresee at this project point are the implementation of sound input and pre-processing with supercollider, and interfacing from supercollider to the speech recognition library and receipt printer. As part of this project is a critical investigation of the strengths and limitations of automatic speech recognition(ASR) technology, I wish intend to delve get more deeply into involved with the internal mechanisms of speech recognition as implemented in the Sphinx-4 library over the course of the term. More substantial A more comprehensive understanding of that technology is necessary to illuminate figure out how to tweak it and expose its internal character and embedded valuesassumptions.
I will update the weekly [[#Progress | Progress]] section as the quarter continues.
Retrieved from "http://wiki.roberttwomey.com/Special:MobileDiff/4311"