Speaker Identification in Multi-Talker Overlapping Speech Using Neural Networks
Open Access
- 17 July 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 134868-134879
Abstract
Although numerous works have studied the problem of automatic speaker identification (SID), there are only few works on the SID for overlapping speech, and none of them consider the case of more than two simultaneous speakers. Recognizing that overlapping speech occurs frequently in real-life scenarios, such as in meetings or debates, this work investigates the methods for overlapping SID (OSID) that can determine identities in the overlapping speech from up to five simultaneous speakers. We propose two deep-learning OSID systems, one is two-stage and the other is single-stage. The two-stage system determines the number of simultaneous speakers firstly, followed by identifying the speaker(s). The single-stage system uses a single classifier to perform OSID directly, which is slightly more computationally efficient than the two-stage system. Our experiments show that the two-stage OSID system achieves better identification accuracy than that of the single-stage system. In addition, both the OSID systems based on one-dimensional convolutional neural networks (1DCNN) perform better than the systems based on multilayer perceptron (MLP) and Gaussian mixture models (GMMs). The proposed 1DCNN-based two-stage OSID system achieves 98.55% OSID accuracy for the clean audio data containing up to five simultaneous speakers. In more challenging experimental conditions involving both background noises and high overlapping energy ratios, the system still attained accuracies of above 90%.Keywords
Funding Information
- Ministry of Science and Technology, Taiwan (MOST 106-2221-E-027-125-MY2)
This publication has 17 references indexed in Scilit:
- Speaker Identification in a Multi-speaker Environment2017
- VoxCeleb: A Large-Scale Speaker Identification Dataset2017
- A review on Deep Learning approaches in Speaker Identification2016
- Deep feature for text-dependent speaker verificationSpeech Communication, 2015
- Deep neural networks for small footprint text-dependent speaker verification2014
- Overlapped speech detection for improved speaker diarization in multiparty meetingsInternational Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2008
- Speaker Overlaps and ASR Errors in Meetings: Effects Before, During, and After the Overlap2006
- Detection of Overlapping Speech in Meetings Using Support Vector Machines and Support Vector RegressionIEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, 2006
- Meetings about meetings: research at ICSI on speech in multiparty conversations2004
- The rich transcription 2004 spring meeting recognition evaluation2004