ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Pseudo Likelihood Correction Technique for Low Resource Accented ASR

Rajpal, A and Mv, AR and Yarra, C and Aggarwal, R and Ghosh, PK (2020) Pseudo Likelihood Correction Technique for Low Resource Accented ASR. In: 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020, 4-8, May 2020, Barcelona, Spain, pp. 7434-7438.

[img] PDF
ica_iee_int_con_aco_spe_sig_pro_pro_7434-7438_2020.pdf - Published Version
Restricted to Registered users only

Download (380kB) | Request a copy
Official URL: https://dx.doi.org/10.1109/ICASSP40776.2020.905364...

Abstract

With the availability of large data, ASRs perform well on native English but poorly for non-native English data. Training nonnative ASRs or adapting a native English ASR is often limited by the availability of data, particularly for low resource scenarios. A typical HMM-DNN based ASR decoding requires pseudo-likelihood of states given an acoustic observation, which changes significantly from native to non-native speech due to accent variation. In order to improve the performance of a native English ASR on non-native English data, we, in this work, propose a DNN-based pseudo-likelihood correction (PLC) technique, in which a non-native pseudo-likelihood vector is mapped to match its native counterpart. Instead of correcting all elements of a non-native pseudo-likelihood vector, a loss function is proposed to correct only top few of them. Experiments with one native and multiple Indian English corpora show an improvement of WER by ~12 and over ~5 using the proposed PLC technique unadapted and adapted native English ASR respectively, when recognition is performed on an Indian English corpus different from that used for both PLC and adaptation. Experiments with upto 2 hours of parallel native and non-native English data reveal that, PLC performs better than adaptation for all unseen cases considered.

Item Type: Conference Paper
Publication: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Publisher: Institute of Electrical and Electronics Engineers Inc.
Additional Information: The copyright of this article belongs to Institute of Electrical and Electronics Engineers Inc.
Department/Centre: Division of Electrical Sciences > Electrical Engineering
Date Deposited: 27 Aug 2020 05:51
Last Modified: 27 Aug 2020 05:51
URI: http://eprints.iisc.ac.in/id/eprint/66372

Actions (login required)

View Item View Item