Language-depedent I-Vectors for LRE15
arXiv:1710.00085v1
Originality Synthesis-oriented
AI Analysis
This is an incremental improvement for language recognition systems, addressing a specific technical issue.
The paper tackles the problem of uncertainty in i-vector extraction for spoken language recognition, particularly for short utterances, by proposing an alternative method to propagate this uncertainty into the backend.
A standard recipe for spoken language recognition is to apply a Gaussian back-end to i-vectors. This ignores the uncertainty in the i-vector extraction, which could be important especially for short utterances. A recent paper by Cumani, Plchot and Fer proposes a solution to propagate that uncertainty into the backend. We propose an alternative method of propagating the uncertainty.