arXiv AI
Rhythm of the Deep: Two-tier acoustic organization of sperm-whale codas from click waveforms to second-order sequence dependence
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Sep 16
Structure Across Voices: Comparing acoustic-event type accumulation and sequence dependence across four vocal repertoires using frozen audio encoders
arXiv:2609.16612v1 Announce Type: cross Abstract: Vocal repertoires can differ in acoustic-event type accumulation and temporal organization, yet direct comparison is difficult because corpora use di...
arXiv AI
Jun 16
Rhythm of the Deep: A Computational-Linguistic Test of Duality of Patterning in Sperm Whale Codas
arXiv:2606. 16084v1 Announce Type: new Abstract: Human language has often been described as combining structure at two levels: lower-level units combine into larger units, which then combine into larger sequences.
arXiv Machine Learning
Jul 27
Phylogenetic signal in marine mammal and bird vocalizations captured by audio foundation models: the limited benefit of domain-specific pretraining
arXiv:2607. 22458v1 Announce Type: new Abstract: Do learned audio embeddings encode structure that nobody told them to encode?
arXiv Computation and Language
Aug 31
Auditing Generative Audio Calls for Known-Task Audio-LLM Evaluation
The paper investigates how to evaluate audio‑language models by separating the use of acoustic evidence from the need to invoke a generative audio model. Using a controlled call‑decision framework, the authors compare policies that rely on transcript labels, encoder outputs from CLAP, AST, or WavLM, and optional calls to generative models such as Qwen2‑Audio, Qwen2.5‑Omni, or MOSS‑Audio. Results on the VocalSound dataset show that while transcript‑only accuracy is low (0.296), encoder‑only controls achieve high accuracy (≈0.85) without any generative calls, and adding generative calls yields only a marginal improvement (0.925 vs. 0.921).
arXiv Computation and Language
Sep 15
Tone on a Budget: A Reference-Free Metric for Lexical Tone in Massively Multilingual Text-to-Speech
arXiv:2609.14817v1 Announce Type: new Abstract: In Yor\`ub\'a, pitch alone separates \d{o}k\d{o} (husband, Mid), \d{o}k\d{\`o} (vehicle, Low), and \d{o}k\d{\'o} (hoe, High) -- the diacritics ARE the...
Hugging Face Trending Papers
Sep 8
TontaubeV1: Streaming Text-to-Speech with Hierarchical Codec Modeling and Bounded Context
TontaubeV1 is a streaming text‑to‑speech model that maintains natural prosody while running on a single consumer GPU. It encodes speech with a hierarchical DualCodec representation at 12.5 Hz, separating a semantic stream from successive acoustic refinements, and uses Qwen3‑derived transformers to predict the semantic stream and add refinements. The model supports up to one minute of reference audio for voice conditioning, streams with a 200 ms latency to first audio, and achieves real‑time factors of 0.08 (single input) and 0.02 (eight concurrent inputs).