Search Results for author:
Found 3 papers, 0 papers with code
Once-for-All Sequence Compression for Self-Supervised Speech Models
The sequence length along the time axis is often the dominant factor of the computation in speech processing.
On Compressing Sequences for Self-Supervised Speech Models
Subsampling while training self-supervised models not only improves the overall performance on downstream tasks under certain frame rates, but also brings significant speed-up in inference.
Don't speak too fast: The impact of data bias on self-supervised speech models
Self-supervised Speech Models (S3Ms) have been proven successful in many speech downstream tasks, like ASR.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
