The Talking Robot: Distortion-Robust Acoustic Models for Robot-Robot Communication

About

We present Artoo, a learned acoustic communication system for robots that replaces hand-designed signal processing with end-to-end co-trained neural networks. Our system pairs a lightweight text-to-speech (TTS) transmitter (1.18M parameters) with a conformer-based automatic speech recognition (ASR) receiver (938K parameters), jointly optimized through a differentiable channel. Unlike human speech, robot-to-robot communication is paralinguistics-free: the system need not preserve timbre, prosody, or naturalness, only maximize decoding accuracy under channel distortion. Through a three-phase co-training curriculum, the TTS transmitter learns to produce distortion-robust acoustic encodings that surpass the baseline under noise, achieving 8.3% CER at 0 dB SNR. The entire system requires only 2.1M parameters (8.4 MB) and runs in under 13 ms end-to-end on a CPU, making it suitable for deployment on resource-constrained robotic platforms.

Hanlong Li, Karishma Kamalahasan, Jiahui Li, Kazuhiro Nakadai, Shreyas Kousik · 2026

Related benchmarks

Task	Dataset	Result
End-to-End Communication Simulation	Communication Simulation 5 dB SNR, 200 characters	Character Error Rate (CER)3.1	7
Acoustic Communication	Isolated Gaussian Noise 5 dB SNR	Character Error Rate (CER)2.1	4
Acoustic Communication	Isolated Pink Noise 5 dB SNR	CER4.8	4
Acoustic Communication	Isolated Brown Noise 5 dB SNR	CER (%)2.6	4
Acoustic Communication	Mixed Noise Gaussian + Pink + Brown (test)	CER at -10 dB38.4	4
End-to-end communication	System Efficiency Evaluation	Latency (ms)11.4	4
End-to-End Communication Simulation	Communication Simulation 5 dB SNR, 10 characters	CER2.4	4
End-to-End Communication Simulation	Communication Simulation 5 dB SNR, 20 characters	CER3.1	4
End-to-End Communication Simulation	Communication Simulation 5 dB SNR, 40 characters	CER4.3	4
End-to-End Communication Simulation	Communication Simulation 5 dB SNR, 60 characters	Character Error Rate4.7	4