arXiv Machine Learning
[b] = [d] - [t] + [p]: Self-supervised Speech Models Discover Phonological Vector Arithmetic
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Jul 13
Phone Segmentation and Recognition through Phonological Activation Mapping
arXiv:2607. 09020v1 Announce Type: cross Abstract: Phone segmentation and recognition are inherently related tasks, yet modern approaches typically model them separately.
arXiv AI
Jun 17
Perceptual compensation for tonal context in self-supervised speech models
arXiv:2606. 17835v1 Announce Type: cross Abstract: This study examines the extent to which the wav2vec2.
arXiv AI
Aug 25
Multi-Task Learning for Non-Canonical Phoneme Recognition via Articulatory Feature Decomposition
The paper proposes a linguistically structured multi‑task learning framework for recognizing non‑canonical phonemes by decomposing phoneme prediction into articulatory feature dimensions such as manner, place, and voicing. A hierarchical architecture with task‑specific heads and a cross‑attention fusion module is combined with semi‑supervised Momentum Pseudo‑Labeling and a cascaded training strategy that gradually introduces articulatory tasks. Experiments on the L2‑ARCTIC dataset demonstrate significant improvements over baseline models and produce interpretable error patterns aligned with phonological feature structure.
Hugging Face Trending Papers
Aug 10
Structured Phonological Representations for Audio-Articulatory rtMRI Speech Classification
Real-time MRI makes it possible to observe vocal-tract articulation during speech, but mapping these articulatory patterns to phonetic and phonological categories remains challenging. We investigate whether PhonoQ, an audio-based model trained to recognize structured phonological features, provides useful information for audio--articulatory modeling.
arXiv Machine Learning
Jul 3
Towards a Phonology-Informed Evaluation of Multilingual TTS
arXiv:2607. 01965v1 Announce Type: cross Abstract: Neural TTS systems can sound natural across languages, but naturalness does not guarantee the preservation of sound contrasts that distinguish words from their grammatical forms.
Hugging Face Trending Papers
Jul 2
Towards a Phonology-Informed Evaluation of Multilingual TTS
Neural TTS systems can sound natural across languages, but naturalness does not guarantee the preservation of sound contrasts that distinguish words from their grammatical forms. Standard metrics like MOS do not test for this.