Speech Recognition

SILENCE, a novel lightweight system, protects user privacy in offloaded speech understanding on resource-constrained devices by selectively masking short-term audio details without impacting long-term…

SepReformer: Asymmetric encoder-decoder model for efficient speech separation, achieving state-of-the-art performance with less computation.

STAR, a novel unsupervised adaptation framework, drastically improves automatic speech recognition (ASR) robustness across diverse domains using only unlabeled data and outperforms existing self-train…

REBORN: An iterative training framework significantly improves unsupervised ASR by learning optimal speech segment boundaries using reinforcement learning, outperforming existing methods.

CA-SSLR: a novel self-supervised learning model dynamically adapts to various speech tasks by integrating language and speaker embeddings, improving performance and reducing reliance on audio features…

Transformers can now perform self-alignment, enabling simpler, faster speech recognition models.