Graduate School and Research Center in Digital Sciences

Speech overlap detection and attribution using convolutive non-negative sparse coding

Vipperla, Ravichander; Geiger, Juergen T; Bozonnet, Simon; Wang, Dong; Evans, Nicholas; Schuller, Bjorn; Rigoll, Gerhard

ICASSP 2012, 37th International Conference on Acoustics, Speech and Signal Processing, March 25-30, 2012, Kyoto, Japan

Overlapping speech is known to degrade speaker diarization performance with impacts on speaker clustering and segmentation. While previous work made important advances in detecting overlapping speech intervals and in attributing them to relevant speakers, the problem remains largely unsolved. This paper reports the first application of convolutive non-negative sparse coding (CNSC) to the overlap problem. CNSC aims to decompose a composite signal into its underlying contributory parts and is thus naturally suited to overlap detection and attribution. Experimental results on NIST RT data show that the CNSC approach gives comparable results to a state-of-the-art hidden Markov model based overlap detector. In a practical diarization system, CNSC based speaker attribution is shown to reduce the speaker error by over 40% relative in overlapping segments.

Document Doi Bibtex

Title:Speech overlap detection and attribution using convolutive non-negative sparse coding
Keywords:overlap detection, speaker attribution, speaker diarization, convolutive non-negative sparse coding
Department:Digital Security
Eurecom ref:3595
Copyright: © 2012 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Bibtex: @inproceedings{EURECOM+3595, doi = {}, year = {2012}, title = {{S}peech overlap detection and attribution using convolutive non-negative sparse coding}, author = {{V}ipperla, {R}avichander and {G}eiger, {J}uergen {T} and {B}ozonnet, {S}imon and {W}ang, {D}ong and {E}vans, {N}icholas and {S}chuller, {B}jorn and {R}igoll, {G}erhard}, booktitle = {{ICASSP} 2012, 37th {I}nternational {C}onference on {A}coustics, {S}peech and {S}ignal {P}rocessing, {M}arch 25-30, 2012, {K}yoto, {J}apan}, address = {{K}yoto, {JAPAN}}, month = {03}, url = {} }
See also: