Toggle Main Menu Toggle Search

Open Access padlockePrints

Informed Single Channel Speech Separation with time-frequency exemplar GMM-HMM model

Lookup NU author(s): Qi Wang, Dr Wai Lok Woo, Emeritus Professor Satnam Dlay, Professor Cheng Chin, Dr Bin Gao


Full text for this publication is not currently held within this repository. Alternative links are provided below where available.


© 2015 IEEE.In recent studies, the problem of Single Channel Speech Separation (SCSS) have been efficiently tackled by introducing additional cues from the original target source in the form of Informed Source Separation (ISS). In this paper, a more realistic situation is considered where an additional user/listener generated Exemplar source is introduced to aid the separation process instead of using the original target source. The Exemplar source consists of patterns that need to be transformed, extracted, regulated and calibrated to generate an utterance dependent (UD) model that could statistically represent the target source. The proposed method uses general speaker independent (SI) features along with the generated UD features are modelled and combined in a joint probability model to achieve reliable separation. Unlike most model-based approaches, the proposed method does not require Speaker Dependent training on individual sources of the mixture, and is therefore much more efficient and less restrictive.

Publication metadata

Author(s): Wang Q, Woo WL, Dlay SS, Chin CS, Gao B

Publication type: Conference Proceedings (inc. Abstract)

Publication status: Published

Conference Name: 2015 IEEE International Conference on Digital Signal Processing (DSP)

Year of Conference: 2015

Pages: 1130-1134

Online publication date: 10/09/2015

Acceptance date: 01/01/1900

Publisher: Institute of Electrical and Electronics Engineers Inc.


DOI: 10.1109/ICDSP.2015.7252055

Library holdings: Search Newcastle University Library for this item

ISBN: 9781479980581