analiza aiqbench
L-Proto addresses the critical challenge of disentangling speaker identity from linguistic cues in multilingual acoustic models, directly advancing machine learning robustness across languages. By enforcing language-consistent training episodes, this method improves generalization on benchmarks like TidyVoice without relying on specific hardware or non-AI infrastructure. This represents a significant step forward for developing universally adaptable speech recognition and verification systems.
L-Proto: Language-Aware Episodic Prototypical Training for Multilingual Speaker Verification
arXiv:2606.17416v1 Announce Type: cross Abstract: Multilingual speaker verification remains challenging because language-dependent acoustic variability causes speaker identity to become entangled with linguistic characteristics, degrading generalization across languages. In multilingual training, embeddings often encode language cues with speaker identity, causing speakers to form language-specific clusters. We propose L-Proto, a language-aware episodic prototypical training strategy that constructs language-consistent episodes. By sampling speakers from a single language per episode, L-Proto reduces language-driven variation during training and encourages embeddings to focus more directly on speaker identity. Experiments on the TidyVoice Challenge benchmark demonstrate consistent performance improvements over conventional fine-tuning and random episodic sampling across multiple backbone architectures.
Abstract:Multilingual speaker verification remains challenging because language-dependent acoustic variability causes speaker identity to become entangled with linguistic characteristics, degrading generalization across languages. In multilingual training, embeddings often encode language cues with speaker identity, causing speakers to form language-specific clusters. We propose L-Proto, a language-aware episodic prototypical training strategy that constructs language-consistent episodes. By sampling speakers from a single language per episode, L-Proto reduces language-driven variation during training and encourages embeddings to focus more directly on speaker identity. Experiments on the TidyVoice Challenge benchmark demonstrate consistent performance improvements over conventional fine-tuning and random episodic sampling across multiple backbone architectures.
Sound (cs.SD); Artificial Intelligence (cs.AI)
arXiv:2606.17416 [cs.SD]
(or arXiv:2606.17416v1 [cs.SD] for this version)
https://doi.org/10.48550/arXiv.2606.17416 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 194 cuvinte