Replacing standard attention with gated focused linear attention makes speech separation models run faster and use less memory while keeping separation quality close to the state of the art.
Some experiments on the recognition of speech, with one and with two ears,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer
Replacing standard attention with gated focused linear attention makes speech separation models run faster and use less memory while keeping separation quality close to the state of the art.