arXiv:2607.25202v2 Announce Type: replace Abstract: Conversational entrainment is well-studied in monolingual and written contexts, but remains underexplored in spoken code-switching (CSW). We presen...
arXiv:2604. 01562v2 Announce Type: replace-cross Abstract: Voice cloning is often evaluated in terms of overall quality, but less is known about accent preservation and its perceptual consequences.
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.
arXiv:2603.08231v2 Announce Type: replace-cross Abstract: Paralinguistic speech tasks are often considered relatively language-agnostic, as they rely on extralinguistic acoustic cues rather than lexi...
arXiv:2609.38887v1 Announce Type: cross Abstract: Real-time voice conversion (VC) systems commonly rely on pretrained speaker embeddings from automatic speaker verification (ASV) models. While effect...
The paper challenges the assumption that improving cross‑lingual alignment automatically enhances cross‑lingual transfer. Using XLM‑R models aligned on token, sentence, and masked‑language‑modeling objectives across four language pairs, the authors evaluate zero‑shot transfer on part‑of‑speech tagging and sentence classification. They find that embedding‑based alignment metrics poorly predict downstream performance and that alignment and task gradients are often nearly orthogonal, especially when operating at different representational levels.
arXiv:2608.30853v1 Announce Type: cross Abstract: While automatic speech recognition (ASR) models have achieved remarkable improvements in recent years, performance disparities persist across differe...
VietPrism is a newly released, large‑scale Vietnamese speech corpus that combines 993.4 hours of real utterances from 1,262 verified speakers with 3.1 k hours of synthetic spoof speech. It uniquely offers transcripts, consistent speaker identities, five dialect groups, and extensive Vietnamese‑English code‑switching—nearly half of the corpus—while pairing each spoof with a matched bona fide utterance. The dataset enables controlled evaluation of deep‑fake detection models, revealing significant variability in detector performance across dialects and speaker similarity.
arXiv:2609.15203v1 Announce Type: cross Abstract: Speaker recognition neural networks learn latent representations (i.e. speaker embeddings) from input utterances to recognise speaker identities. How...
The study compares an English-only and a bilingual decoder-only model, each 310 M parameters, trained on eight diverse languages while controlling for English exposure, compute, and document overlap. After aligning on shared English vocabulary, the authors find that token embeddings appear similar, but the deeper hidden states used for prediction diverge across models. This hidden‑state mismatch grows through middle transformer layers and persists despite controls, indicating that contextual processing differs between the models. "whyItMatters":"The findings show that embedding alignment can conceal significant internal representation differences, which is crucial for any downstream work that assumes aligned multilingual models are interchangeable."
The study investigates whether monolingual language models, trained without joint multilingual objectives, develop cross-lingual alignment. By evaluating models such as Goldfish and independently built monolingual systems, the authors find that alignable representational geometry emerges across layers, strengthening with larger data, larger models, or closer linguistic proximity. A single Procrustes rotation on parallel sentences can map hidden states between models, and applying this rotation to a German model’s residuals swaps factual predictions to those of the donor English model, demonstrating functional transfer.
arXiv:2606. 06740v1 Announce Type: cross Abstract: Discrete speech units obtained via k-means clustering of self supervised embeddings entangle phonetic, speaker, and language information, causing speaker mixing and cross-lingual interference in multilingual multi-speaker speech generation.