%Aigaion2 BibTeX export from Idiap Publications %Saturday 23 November 2024 05:51:10 AM @INPROCEEDINGS{Imseng_ASRU_2011, author = {Imseng, David and Rasipuram, Ramya and Magimai.-Doss, Mathew}, projects = {Idiap, IM2}, month = dec, title = {Fast and flexible Kullback-Leibler divergence based acoustic modeling for non-native speech recognition}, booktitle = {Proceedings of the IEEE workshop on Automatic Speech Recognition and Understanding}, year = {2011}, pages = {348-353}, location = {Hawaii, USA}, crossref = {Imseng_Idiap-RR-01-2012}, abstract = {One of the main challenge in non-native speech recognition is how to handle acoustic variability present in multiaccented non-native speech with limited amount of training data. In this paper, we investigate an approach that addresses this challenge by using Kullback-Leibler divergence based hidden Markov models (KL-HMM). More precisely, the acoustic variability in the multi-accented speech is handled by using multilingual phoneme posterior probabilities, estimated by a multilayer perceptron trained on auxiliary data, as input feature for the KL-HMM system. With limited training data, we then build better acoustic models by exploiting the advantage that the KL-HMM system has fewer number of parameters. On HIWIRE corpus, the proposed approach yields a performance of 1.9\% word error rate (WER) with 149 minutes of training data and a performance of 5.5\% WER with 2 minutes of training data.}, pdf = {https://publications.idiap.ch/attachments/papers/2011/Imseng_ASRU_2011.pdf} } crossreferenced publications: @TECHREPORT{Imseng_Idiap-RR-01-2012, author = {Imseng, David and Rasipuram, Ramya and Magimai.-Doss, Mathew}, keywords = {Hidden Markov Model, Kullback-Leibler divergence, multilayer perceptron, Posterior features}, projects = {Idiap, IM2}, month = {1}, title = {Fast and flexible Kullback-Leibler divergence based acoustic modeling for non-native speech recognition}, type = {Idiap-RR}, number = {Idiap-RR-01-2012}, year = {2012}, institution = {Idiap}, abstract = {One of the main challenge in non-native speech recognition is how to handle acoustic variability present in multiaccented non-native speech with limited amount of training data. In this paper, we investigate an approach that addresses this challenge by using Kullback-Leibler divergence based hidden Markov models (KL-HMM). More precisely, the acoustic variability in the multi-accented speech is handled by using multilingual phoneme posterior probabilities, estimated by a multilayer perceptron trained on auxiliary data, as input feature for the KL-HMM system. With limited training data, we then build better acoustic models by exploiting the advantage that the KL-HMM system has fewer number of parameters. On HIWIRE corpus, the proposed approach yields a performance of 1.9\% word error rate (WER) with 149 minutes of training data and a performance of 5.5\% WER with 2 minutes of training data.}, pdf = {https://publications.idiap.ch/attachments/reports/2011/Imseng_Idiap-RR-01-2012.pdf} }