In:
Proceedings of the AAAI Conference on Artificial Intelligence, Association for the Advancement of Artificial Intelligence (AAAI), Vol. 35, No. 16 ( 2021-05-18), p. 13961-13969
Abstract:
We study the cocktail party problem and propose a novel attention network called Tune-In, abbreviated for training under negative environments with interference. It firstly learns two separate spaces of speaker-knowledge and speech-stimuli based on a shared feature space, where a new block structure is designed as the building block for all spaces, and then cooperatively solves different tasks. Between the two spaces, information is cast towards each other via a novel cross- and dual-attention mechanism, mimicking the bottom-up and top-down processes of a human's cocktail party effect. It turns out that substantially discriminative and generalizable speaker representations can be learnt in severely interfered conditions via our self-supervised training. The experimental results verify this seeming paradox. The learnt speaker embedding has superior discriminative power than a standard speaker verification method; meanwhile, Tune-In achieves remarkably better speech separation performances in terms of SI-SNRi and SDRi consistently in all test modes, and especially at lower memory and computational consumption, than state-of-the-art benchmark systems.
Type of Medium:
Online Resource
ISSN:
2374-3468
,
2159-5399
DOI:
10.1609/aaai.v35i16.17644
Language:
Unknown
Publisher:
Association for the Advancement of Artificial Intelligence (AAAI)
Publication Date:
2021
Permalink
