AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Modeling Attention and Memory for Auditory Selection in a Cocktail Party Environment

Jiaming Xu, Jing Shi, Guangcan Liu, Xiuyi Chen, Bo Xu

AAAI 2018 · Architectures and efficiency › Attention and transformers · approach: State space and recurrent sequence models · 25 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace life-long memory with a speaker embedding matrix (ASAM-spk) (ablation)ASAM · WSJ0 two-speaker, top-downGNSDR: 7.46 -> 8.16Mixed
replace life-long memory with a speaker embedding matrix (ASAM-spk) (ablation)ASAM · WSJ0 two-speaker plus street noiseGNSDR: 4.36 -> 3.92Hurt
use ASAM instead of deep clustering without noise threshold under real noiseDC · WSJ0 two-speaker plus street noiseGNSDR: 2.61 -> 4.36Improved
use ASAM instead of best DC (-40) on clean two-speaker mixturesDC (-40) · WSJ0 two-speakerGNSDR: 7.47 -> 7.46No clear effect
use ASAM instead of DC (-40) on three-speaker THCHS-30DC (-40) · THCHS-30 three-speakerGNSDR: 5.48 -> 5.02Hurt
add background noise threshold to deep clustering (-40 dB)DC · WSJ0 two-speakerGNSDR: 4.78 -> 7.47Improved
longer stimulus duration for unknown speaker memory (ablation)ASAM · bottom-up attention, two unknown speakersGNSDRImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy