arXiv:2606. 16595v1 Announce Type: cross Abstract: Zero-shot cross-lingual phoneme recognition is often hindered by the fragility of direct acoustic-to-symbol mapping, which is susceptible to language-specific variations.
arXiv:2606. 05173v1 Announce Type: cross Abstract: Masked language modelling (MLM) has been the dominant pre-training objective for text encoders since BERT, yet it encourages representations that are strongly anchored to surface-form token identity rather than deeper semantic structure.
arXiv:2606. 05678v1 Announce Type: cross Abstract: Automatic speech recognition (ASR) systems have become widely used for multilingual speech-to-text transcription.
arXiv:2607. 09020v1 Announce Type: cross Abstract: Phone segmentation and recognition are inherently related tasks, yet modern approaches typically model them separately.
arXiv:2606. 25225v1 Announce Type: cross Abstract: Self-supervised learning from large-scale video data has emerged as a dominant paradigm for visual representation learning.
arXiv:2606. 30356v1 Announce Type: cross Abstract: We propose Online Latent prediction with Invariant Views and rEconstruction (OLIVE), a self-supervised speech representation learning framework that jointly optimizes analysis and synthesis objectives.
Self-supervised learning from large-scale video data has emerged as a dominant paradigm for visual representation learning. Since audio and visual streams naturally co-occur in video data, extending this success to jointly learn from both modalities is a natural next step, yet it remains challenging.
arXiv:2603. 29042v2 Announce Type: replace-cross Abstract: Phone recognition (PR) is a key enabler of multilingual and low-resource speech processing tasks, yet robust performance remains elusive.
arXiv:2605. 03297v2 Announce Type: replace-cross Abstract: ASR systems based on self-supervised acoustic pretraining and CTC fine-tuning achieve strong performance on native speech but remain sensitive to accent variability.
Recent advances in zero-shot text-to-speech (TTS) have substantially improved speech quality and voice cloning fidelity. However, many zero-shot TTS systems still depend on audio prompt transcripts at inference time.
arXiv:2607. 15295v1 Announce Type: cross Abstract: We present AV-JEPA, an elegant multimodal extension of LeJEPA to audio-visual self-supervised learning.
arXiv:2607. 00784v1 Announce Type: cross Abstract: Vision-language pretraining remains dominated by contrastive objectives, whereas vision-only self-supervised learning has largely adopted non-contrastive methods.
arXiv:2606. 10278v1 Announce Type: cross Abstract: Speech Emotion Recognition (SER) aims to identify a speaker's emotional state from audio signals.