Author ORCID Identifier

https://orcid.org/0009-0005-1251-5460

Document Type

Thesis

Date of Award

2026

Degree Name

Master of Science (MS)

Department

Computer Science

First Advisor

Rodrigue Rizk

Abstract

This thesis presents a proof-of-concept communication system in which two local large language model endpoints communicate across a simulated analog telephone line using legacy USB modems. The project combines modem voice mode, modem data mode, local speech processing, and structured machine messaging into a single staged session. During the voice phase, one endpoint places a call, the other answers, speech generated by a locally hosted LLaMA-family model is synthesized with Piper, transmitted through the modem voice path, captured on the remote side, and transcribed with Faster-Whisper to drive the next response. After the voice exchange, the system transitions to a data phase through modem control logic, using same-call switching when supported and a redial-based fallback when necessary. In the data phase, a custom framed transport with sequence numbers, CRC-16 validation, acknowledgments, retransmission, and duplicate suppression carries JSON-RPC 2.0 messages and a minimal implementation of the Model Context Protocol, including initialization, ping, tools/list, and tools/call for a server-status tool. The system demonstrates that modern local AI components can operate meaningfully over constrained legacy telephony hardware while exposing the contrast between human-legible speech and machine-legible protocol exchange. Its contribution is not improved throughput over conventional networks, but a transparent and physically demonstrable example of adaptive communication across mixed representational modes.

Subject Categories

Artificial Intelligence and Robotics | Communication | Software Engineering

Keywords

JSON-RPC, Large language models, Model Context Protocol, modem communication, simulated telephone line

Number of Pages

79

Publisher

University of South Dakota

Download

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.