A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit <a rel="external noopener" href="https://www.isca-speech.org/archive/pdfs/interspeech_2019/kitza19_interspeech.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
Cumulative Adaptation for BLSTM Acoustic Models
<span title="2019-09-15">2019</span>
<i title="ISCA">
<a target="_blank" rel="noopener" href="https://fatcat.wiki/container/trpytsxgozamtbp7emuvz2ypra" style="color: black;">Interspeech 2019</a>
</i>
Preserved Fulltext
This paper addresses the robust speech recognition problem as an adaptation task. Specifically, we investigate the cumulative application of adaptation methods. A bidirectional Long Short-Term Memory (BLSTM) based neural network, capable of learning temporal relationships and translation invariant representations, is used for robust acoustic modeling. Further, ivectors were used as an input to the neural network to perform instantaneous speaker and environment adaptation, providing 8% relative
<span class="external-identifiers">
<a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.21437/interspeech.2019-2162">doi:10.21437/interspeech.2019-2162</a>
<a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/interspeech/KitzaGSN19.html">dblp:conf/interspeech/KitzaGSN19</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xmtnbche35grxnx7kmdoftwndu">fatcat:xmtnbche35grxnx7kmdoftwndu</a>
</span>
more »
... mprovement in word error rate on the NIST Hub5 2000 evaluation testset. By enhancing the first-pass i-vector based adaptation with a second-pass adaptation using speaker and environment dependent transformations within the network, a further relative improvement of 5% in word error rate was achieved. We have reevaluated the features used to estimate ivectors and their normalization to achieve the best performance in a modern large scale automatic speech recognition system.
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211208021628/https://www.isca-speech.org/archive/pdfs/interspeech_2019/kitza19_interspeech.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext">
<button class="ui simple right pointing dropdown compact black labeled icon button serp-button">
<i class="icon ia-icon"></i>
Web Archive
[PDF]
<div class="menu fulltext-thumbnail">
<img src="https://blobs.fatcat.wiki/thumbnail/pdf/58/78/5878ec15ea7f20890fc87eeb9b3eea559377b643.180px.jpg" alt="fulltext thumbnail" loading="lazy">
</div>
</button>
</a>
<a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.21437/interspeech.2019-2162">
<button class="ui left aligned compact blue labeled icon button serp-button">
<i class="external alternate icon"></i>
Publisher / doi.org
</button>
</a>