betaFeedback

WorksEngineering

Layer-wise Linear Probing of an Encoder-free Audio-capable Language Model

Abstract

Encoder-free audio-capable multimodal language models pro- vide a unique setting for studying how speech representations emerge inside a language-model decoder. In Gemma-4-12B, short waveform frames are projected directly into the shared embedding space, and all subsequent contextual processing is performed by the decoder layers. We use this architecture to examine where acoustic, phonetic, segmental, and paralinguis- tic information becomes linearly accessible across depth. Us- ing the TIMIT corpus, we extract all 49 representations from the frozen model, including the embedding output and the out- puts of its 48 decoder layers. We train linear probes for log- F0, log-energy, voicing, phone identity, word-onset structure, speaker identity, recorded speaker gender, and dialect-region labels. The results show a broad progression in linear acces- sibility. Acoustic properties are most strongly decodable in the early layers, paralinguistic attributes are most accessible in the early-to-middle layers, and phone identity and boundary- sensitive information reach their highest performance around layer 11. Several properties remain strongly decodable across broad near-peak regions rather than at a single uniquely optimal layer. In deeper layers, phone identity and closed-set speaker identity decline sharply, while voicing, log-F0, and gender re- main more accessible. These findings provide an initial map of how speech information develops when the decoder is the first contextual stage to process audio.

Paper details

vlnc:W_8s4trbs2
Version
v1 · latest
Published
Fresh — added to the Hub within the last 30 days
Added
License
arXiv nonexclusive license
Usage

views · 0

downloads · 0

A view counts once per browser per day, a download each time the PDF is requested.

  • Engineering

Generative AI tools

View statement
Looking for related papers…