arXiv AI August 26, 2026 By Qixin Deng, Bryan Pardo, Thrasyvoulos N Pappas

Do Joint Language-Audio Embeddings Encode Perceptual Timbre Semantics?

The paper investigates whether joint language‑audio embedding models encode human perceptual timbre semantics. It evaluates several state‑of‑the‑art models, finding that LAION‑CLAP aligns best with human‑perceived timbre across instrumental sounds and descriptor‑conditioned audio effects, yet the overall alignment remains limited. The study also notes that reverb‑induced timbre semantics are more consistently captured than equalization‑induced ones.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Jul 7

Probing Low-Level Acoustic Attribute Encoding in CLAP Audio Embeddings

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.

By H\'ector Martel, Joe Hennessy-Priest, Taemin Cho

rag multimodal

arXiv AI

Jun 8

FIGMA: Towards FIne-Grained Music retrievAl

arXiv:2606. 06615v1 Announce Type: cross Abstract: Retrieving music using natural language descriptions has improved with contrastive audio-text models such as CLAP, but current systems remain limited to coarse semantic queries.

By Nishit Anand, Ashish Seth, Sreyan Ghosh, Dinesh Manocha, Ramani Duraiswami

benchmarks safety

arXiv Computation and Language

Sep 3

SonicCaps: Large-Scale Diverse and Fine-Grained Captioning for Improved Audio-Retrieval

SonicCaps is a large-scale audio captioning dataset featuring approximately 15 million captions paired with 700,000 audio clips, created using the Qwen3-Omni multimodal language model. The dataset emphasizes diversity by generating around 24 captions per clip through structured prompt engineering and few-shot generation, covering main descriptions, rephrased variants, and semantic tags. Human evaluations rate SonicCaps higher than existing datasets, and training CLAP models on it improves audio retrieval and zero-shot classification across public and commercial benchmarks.

By Zineb Lahrichi, Marc Ferras, Ga\"el Richard, Geoffroy Peeters

llms multimodal benchmarks

arXiv Machine Learning

Jul 31

Integrating Contextual Embeddings into Evaluation of Expressive MIDI Piano Performances

arXiv:2607. 27909v1 Announce Type: cross Abstract: Objective evaluation of expressive MIDI piano performances typically relies on attribute statistics such as timing, velocity, and duration of individual notes.

By Dmitrii Gavrilev, Ilya Borovik, Vladimir Viro

rag safety

arXiv AI

Jul 15

The Sound of Absence: Audio-Language Embedding Models Struggle with Negation

arXiv:2607. 12290v1 Announce Type: cross Abstract: Audio-language embedding models such as CLAP are widely evaluated on matching present sound events, but rarely on negation.

By Chun-Yi Kuan, Hung-yi Lee

llms rag multimodal safety

arXiv AI

Jul 1

ALM2Vec: Learning Audio Embeddings for Universal Audio Retrieval with Large Audio-Language Models

arXiv:2606. 30682v1 Announce Type: cross Abstract: Recent advances in language--audio retrieval have been largely driven by contrastive dual-encoder architectures that align audio and text in a shared embedding space.

By Fengjie Lu, Chenang Jiang, Jiarui Hai, Helin Wang, Aaron Yee

llms rag nlp multimodal benchmarks

One email a morning, machine-written

Related stories

Probing Low-Level Acoustic Attribute Encoding in CLAP Audio Embeddings

FIGMA: Towards FIne-Grained Music retrievAl

SonicCaps: Large-Scale Diverse and Fine-Grained Captioning for Improved Audio-Retrieval

Integrating Contextual Embeddings into Evaluation of Expressive MIDI Piano Performances

The Sound of Absence: Audio-Language Embedding Models Struggle with Negation

ALM2Vec: Learning Audio Embeddings for Universal Audio Retrieval with Large Audio-Language Models