Unsupervised Filterbank Learning for Speech-based Access System for Agricultural Commodity

Sailor, HB and Patil, HA and Rajpal, A (2018) Unsupervised Filterbank Learning for Speech-based Access System for Agricultural Commodity. In: 9th International Conference on Advances in Pattern Recognition, ICAPR 2017, 27 - 30 December 2017, Bangalore, pp. 210-215.

PDF ICAPR _2017.pdf - Published Version Restricted to Registered users only Download (788kB) | Request a copy

Abstract

This paper presents an automatic speech recognition (ASR) system developed as a part of a speech-based access system for an agricultural commodity in the Gujarati language. Speech database was collected from the farmers in the villages of Gujarat state (India) with various dialectal variations and real noisy acoustic environments. We have used the recently proposed Convolutional Restricted Boltzmann Machine (ConvRBM) to learn the filterbank as a front-end. Self-taught learning framework is applied to train Conv RBM using extra Gujarati speech database other than an agricultural commodity. Stochastic data sweeping technique is used to enhance the training speed of ConvRBM. Experiments using time delay deep neural networks (TDNNs) show that ConvRBM features give relative improvements of 5.5 in WER compared to the Mel filterbank features. The system-level combination of both features further improves the performance (3.55 absolute reduction in WER).

Item Type:	Conference Paper
Publication:	2017 9th International Conference on Advances in Pattern Recognition, ICAPR 2017
Publisher:	Institute of Electrical and Electronics Engineers Inc.
Additional Information:	The copyright for this article belongs to the Institute of Electrical and Electronics Engineers Inc.
Keywords:	Agriculture; Convolution; Deep neural networks; Filter banks; Speech; Stochastic systems, Absolute reduction; Acoustic environment; Agricultural commodities; Automatic speech recognition system; Convolutional RBM; Dialectal variation; Restricted boltzmann machine; Self-taught learning, Speech recognition
Department/Centre:	Division of Electrical Sciences > Electrical Communication Engineering Division of Interdisciplinary Sciences > Computational and Data Sciences
Date Deposited:	28 Jul 2022 10:27
Last Modified:	28 Jul 2022 10:27
URI:	https://eprints.iisc.ac.in/id/eprint/75033

Actions (login required)

View Item