Tag
Myovox decodes open-vocabulary English text from 31-channel surface electromyography recorded from facial muscles, achieving an 18.53% word error rate on the emg2speech General Corpus through decode correction, bidirectional Conformer training with cross-modal distillation, and language model reranking.
This paper introduces a method for word-level timestamping in Speech Large Language Models using relative time intervals and masked training to enhance prediction accuracy and robustness against noisy real-world annotations.
Eigendrum is a web tool that allows users to draw shapes and hear them as real drums by solving eigenvalue problems for drumhead vibrations using finite element methods.
This paper proposes evaluating speech articulation synthesis using phoneme recognition with articulatory features, addressing limitations of traditional metrics like point-wise distance. Experiments on a single-speaker RT-MRI dataset show the approach captures phonetic nuances and improves assessment.