Conversation piece: A speech-based interactive art installation
Bibliographic record
Abstract
A speech-based interactive art installation creating an intelligent room that can hold conversations with its occupants. Wright's project poses the fundamental question: is meaningful social interaction with a machine possible? Art/science collaboration with\n\nUCL and University of Edinburgh. Conversation Piece is a speech-based interactive art installation (approx 10m x 12m) that enables individual audience members\n\nto apparently converse with the gallery space itself (see portfolio/URL for details).\n\nThis work built on Wright’s previous art/science research to explore, via artistic practice, issues of interactivity and response\n\nthrough spoken language. The installation created a transparent interface between the virtual and the 'real' using synthesised\n\nspoken voice and concealed microphone arrays. Conversation Piece follows in the tradition of chatbots such as Eliza and\n\nJabberwacky, although by using spoken voice and intelligently constructed conversations, it significantly improves the user's\n\nexperience of identification and communication with the machine. The installation is broadly accessible, and aims to raise\n\nquestions about human/machine interaction that equally interest scientists, technologists and art audiences.\n\nThe work was tested on audiences at several key stages of development – both to enable further development of the technology\n\nand the artificial intelligence, and to determine audience response. It was on public exhibition (alongside 9 other artists) at\n\nAugsburg, a key venue for this field, where Wright and Lincoln also presented their research findings. Other presentations\n\ninclude Toronto (May 2007) and UCL (April and November 2007).\n\nConversation Piece represents a major body of interdisciplinary research in computer generated speech and language\n\nrecognition, which is being carried out in collaboration with UCL and the Department of Speech and Language, Edinburgh\n\nUniversity (a world leader for speech technologies). It was enabled through an AHRC Arts Science Fellowship and a Wellcome\n\nTrust Sci-Art production award. It is the first collaboration between an artist, scientist and cutting-edge computer technologist on\n\nthis scale and formed an AHRC case study of good practice in Art-Science Collaborations.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.004 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.121 | 0.023 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".