self-supervised speech models
PulseAugur coverage of self-supervised speech models — every cluster mentioning self-supervised speech models across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
Self-supervised speech models exhibit phonological vector arithmetic
Researchers have discovered that self-supervised speech models (S3Ms) encode phonological features in a structured, compositional manner. A study across 96 languages revealed linear directions within S3M representations…
-
New research tackles deepfake detection with cross-lingual and multimodal approaches · 4 sources tracked
Researchers are developing advanced methods for detecting audio and video deepfakes, focusing on improving generalization across different languages and unseen attack types. One approach, Language Orthogonalization, aim…
-
New SPAM method jointly tackles phone segmentation and recognition
Researchers have developed a novel method called S3M-based Phonological Activation Mapping (SPAM) to jointly address phone segmentation and recognition tasks in speech processing. This approach leverages the latent phon…
-
New system PhonoQ-2.0 advances multilingual phonological feature recognition
Researchers have developed PhonoQ-2.0, a new multilingual system for recognizing phonological features in speech. This system utilizes self-supervised speech models to predict a detailed 22-dimensional feature vector pe…