arXiv:2607. 09020v1 Announce Type: cross Abstract: Phone segmentation and recognition are inherently related tasks, yet modern approaches typically model them separately.
arXiv:2606. 17835v1 Announce Type: cross Abstract: This study examines the extent to which the wav2vec2.
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.
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: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.
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.
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...
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:2609.10434v1 Announce Type: new Abstract: Self-supervised speech foundation models are now used in a wide array of downstream applications, including traditional speech recognition and as the b...
The paper introduces an Encoding Probe that reconstructs language model representations using interpretable features, addressing limitations of traditional decoding probes such as incomparable feature contributions and correlation effects. It evaluates this approach on text and speech transformer models, examining features from acoustics, phonetics, syntax, lexicon, and speaker identity. Findings reveal that speaker-related effects vary with training objectives and datasets, while syntactic and lexical features independently contribute to reconstruction, offering a complementary perspective on model interpretation.
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:2609.13045v1 Announce Type: new Abstract: Speech-to-speech translation (S2ST) has advanced significantly with speech LLMs, offering the potential for joint optimization and preserving non-lingu...