The paper investigates how large audio‑language models (LALMs) integrate audio and text representations. By identifying cross‑modal neurons that encode both modalities, the authors demonstrate that audio and text representations align within a shared subspace across three LALMs and four acoustic attribute types. Causal interventions on these neurons confirm their necessity for prediction and show they can be manipulated to steer model outputs.
arXiv:2502. 14671v4 Announce Type: replace-cross Abstract: Large Language Model (LLM) representations are known to align with brain activity during language processing, but it remains unclear what drives this alignment.
The paper investigates whether audio‑language models capture paralinguistic cues beyond spoken content. Using the Expresso dataset and four open‑source models, the authors trace how speaking style information is encoded in the late layers of the audio encoder but is degraded before reaching the final output. They find that some models are content‑driven while others are acoustic‑driven, revealing a gap between what is encoded and what is utilized in current audio‑language models.
BAT-CLIP is a trimodal alignment framework that jointly aligns intracranial EEG (iEEG) neural embeddings to both pretrained audio and text anchors within a shared, frozen audio‑text manifold. Unlike existing CLIP‑style brain‑speech models that anchor neural activity to a single modality, BAT‑CLIP leverages both audio and text to preserve temporal structure and linguistic separability. On the naturalistic Podcast benchmark, BAT‑CLIP produces more robust representations than bimodal CLIP baselines and demonstrates the value of self‑supervised foundation models for CLIP training.
arXiv:2606. 18273v1 Announce Type: cross Abstract: Large audio language models (LALMs) have shown impressive capabilities on diverse audio understanding tasks, ranging from speech transcription to music analysis.
arXiv:2605. 00025v3 Announce Type: replace-cross Abstract: Speech neuroprosthesis systems decode intended speech from neural activity in the absence of audible output, offering a path to restoring communication for individuals with speech-impairing conditions.
arXiv:2610.23745v1 Announce Type: cross Abstract: Recent large audio language models (LALMs) have extended their capabilities beyond lexical speech understanding to tasks requiring paralinguistic and...
arXiv:2607. 11801v1 Announce Type: cross Abstract: Large audio-language models (LALMs) often underperform on fine-grained, non-semantic attributes of speech, such as a speaker's emotion, despite strong performance on speech content.
arXiv:2603. 09714v2 Announce Type: replace-cross Abstract: While multi-audio understanding is critical for large audio-language models (LALMs), it remains underexplored.
The study applies causal tracing to large audio language models (LALMs) to uncover how they fuse acoustic and textual information. Layer‑wise analysis reveals distinct fusion strategies—progressive integration in DeSTA versus abrupt late‑stage fusion in Qwen—while token‑wise analysis identifies the final sequence token as an informational bottleneck that decisively retrieves audio content. Additionally, an attention‑like query mechanism at intermediate tokens is observed, prompting the model to pull task‑relevant audio context.
DEAF (Diagnostic Evaluation of Acoustic Faithfulness) is a benchmark comprising over 2,700 conflict stimuli that test Audio Multimodal Large Language Models (Audio MLLMs) across three acoustic dimensions: emotional prosody, background sounds, and speaker identity. The benchmark uses a controlled multi-level evaluation framework that gradually increases textual influence, from semantic conflicts to misleading prompts, to separate content-driven bias from prompt-induced sycophancy. Diagnostic metrics are introduced to measure how much models rely on textual cues versus acoustic signals, and an evaluation of seven Audio MLLMs shows that while models respond to acoustic variations, their predictions are largely driven by textual inputs, highlighting a gap between benchmark performance and true acoustic understanding.
arXiv:2607. 03806v1 Announce Type: cross Abstract: Audio foundation models are widely adopted as general-purpose feature extractors, yet the internal structure of their learned representations remains insufficiently understood.
arXiv:2607.10162v2 Announce Type: replace-cross Abstract: Sound symbolism, the human tendency to map speech sounds to perceptual qualities such as roundness or sharpness, arises primarily from the ac...