arXiv:2610.09486v1 Announce Type: cross Abstract: Spoken language identification (LID) aims to recognize the target language regardless of accent. In practice, however, LID models fine-tuned from sel...
arXiv:2609.28060v1 Announce Type: new Abstract: Self-supervised speech models encode rich phonetic information, but it remains unclear how to transform this information into interpretable metrics for...
Self-supervised speech models encode rich phonetic information, but it remains unclear how to transform this information into interpretable metrics for second-language (L2) pronunciation assessment in...
arXiv:2606. 20137v1 Announce Type: cross Abstract: Existing mean opinion score (MOS) prediction models typically predict utterance-level naturalness MOS and can be insensitive to localized pitch-accent errors.
The paper proposes a method called language orthogonalization to improve zero‑shot cross‑lingual audio deepfake detection. By removing language‑dependent variation from self‑supervised speech models using a target‑free ridge map on language‑identification embeddings, the approach consistently lowers equal error rates across six languages and six model backbones. The gains are larger when the target language is more distant in the language‑identification space.
The paper introduces a native-reference phone‑class geometry that measures second‑language pronunciation deviation without needing pronunciation labels, read‑aloud prompts, or matched native recordings. By averaging self‑supervised representations for each phone‑class in a native speech corpus and applying singular value decomposition, the authors create a compact coordinate system. Projecting L2 utterances into this space, they find that distances to native coordinates correlate negatively with holistic speaking proficiency and pronunciation quality, indicating the geometry captures relevant acoustic‑phonetic information for spontaneous L2 speech.
Audio deepfake detectors need to transfer to languages absent from training, as multilingual speech synthesis outpaces labeled anti-spoofing resources. While detectors increasingly rely on self-superv...
arXiv:2606. 17835v1 Announce Type: cross Abstract: This study examines the extent to which the wav2vec2.
arXiv:2606. 11542v1 Announce Type: cross Abstract: Modern pretrained self-supervised automatic speech recognition models are trained on large-scale audio data to encode speech into contextualized representations.
arXiv:2607. 03928v1 Announce Type: cross Abstract: Accent normalization (AN) seeks to convert non-native (L2) accented speech into standard (L1) speech while preserving speaker identity.
The paper investigates whether audio‑language models capture paralinguistic cues beyond spoken content. Using the Expresso dataset and four open‑source models, the authors trace how speaking style information is encoded in the late layers of the audio encoder but is degraded before reaching the final output. They find that some models are content‑driven while others are acoustic‑driven, revealing a gap between what is encoded and what is utilized in current audio‑language models.
The paper evaluates the robustness of DistilHuBERT for accent classification using speaker‑disjoint splits and cross‑corpus tests with L2‑ARCTIC and other English accent datasets. It finds a large performance gap between in‑corpus and external evaluations, indicating that file‑level tests overestimate accuracy. The study shows that balanced external‑data training performs best, while pseudo‑labeling with confidence filtering is insufficient under domain mismatch.