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

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.

Authors

Publication Details

Journal
arXiv (Cornell University)
Published
2026-11-16
DOI
https://doi.org/10.48550/arxiv.2611.20954
Primary Topic
Speech Recognition and Synthesis
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

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

Sishir Kalita, Parismita Gogoi, S. R. Mahadeva Prasanna, Laishram Rahul et al.
arXiv (Cornell University)
Speech Recognition and Synthesis
preprint

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

Sishir Kalita, Parismita Gogoi, S. R. Mahadeva Prasanna, Laishram Rahul, Deepak KT, Shruthi B. S.
preprint en

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.

arXiv (Cornell University)
Speech Recognition and Synthesis
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon