SOURCE-LINKED INTELLIGENCE

TokenMapper: A Step Toward Interoperable Speech Token Translation

arXiv · AI, language, vision and robotics · article · Sep 11, 2026 · UTC

Neural audio codecs discretize speech into token sequences, but the resulting token spaces differ in vocabulary and codebook structure, preventing direct communication across models. This limitation affects applications such as conversational voice agents and speech to speech translation systems where multiple speech models must interact. As a result, transferring information between speech systems typically requires decoding to waveform audio and re-encoding with a second tokenizer, increasing latency and introducing potential information loss. To address these limitations, we present TokenMa

Read original source ↗ Open in workspace

recordType

paper

region

Global