3-D CNN MODELS FOR FAR-FIELD MULTI-CHANNEL SPEECH RECOGNITION

Ganapathy, Sriram and Peddinti, Vijayaditya (2018) 3-D CNN MODELS FOR FAR-FIELD MULTI-CHANNEL SPEECH RECOGNITION. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), APR 15-20, 2018, Calgary, CANADA, pp. 5499-5503.

PDF Ieee_Int_Con_Aco_Spe_Sig_Pro_5499_2018.pdf - Published Version Restricted to Registered users only Download (487kB) | Request a copy

Abstract

Automatic speech recognition (ASR) in far-field reverberant environments, especially when involving natural conversational multiparty speech conditions, is challenging even with the state-of-theart recognition methodologies. The two main issues are artifacts in the signal due to reverberation and the presence of multiple speakers. In this paper, we propose a three dimensional (3-D) convolutional neural network (CNN) architecture for multi-channel far-field ASR. This architecture processes time, frequency & channel dimensions of the input spectrogram to learn representations using convolutional layers. Experiments are performed on the REVERB challenge LVCSR task and the augmented multi-party (AMI) LVCSR task using the array microphone recordings. The proposed method shows improvements over the baseline system that uses beamforming of the multi-channel audio along with a 2-D conventional CNN framework (absolute improvements of 1.1 % over the beamformed baseline system on AMI dataset).

Item Type:	Conference Proceedings
Publisher:	IEEE
Additional Information:	Copy right for this article belong to IEEE
Keywords:	Far-field speech recognition; 3D CNN modeling; Multi-party conversational speech
Department/Centre:	Division of Electrical Sciences > Electrical Engineering
Date Deposited:	26 Oct 2018 14:44
Last Modified:	26 Oct 2018 14:44
URI:	http://eprints.iisc.ac.in/id/eprint/60965

Actions (login required)

View Item