Publication Details
Unsupervised Language Model Adaptation for Speech Recognition with no Extra Resources
speech recognition
Classically, automatic speech recognition (ASR) models are decomposed into
acoustic models and language models (LM). LMs usually exploit the linguistic
structure on a purely textual level and usually contribute strongly to an ASR
systems performance. LMs are estimated on large amounts of textual data covering
the target domain. However, most utterances cover more specic topics, e.g. in
uencing the vocabulary used. Therefore, it's desirable to have the LM adjusted to
an utterance's topic. Previous work achieves this by crawling extra data from the
web or by using signicant amounts of previous speech data to train topic-specic
LM on. We propose a way of adapting the LM directly using the target utterance to
be recognized. The corresponding adaptation needs to be done in an unsupervised
or automatically supervised way based on the speech input. To deal with
corresponding errors robustly, we employ topic encodings from the recently
proposed Subspace Multinomial Model. This model also avoids any need of explicit
topic labelling during training or recognition, making the proposed method
straight-forward to use. We demonstrate the performance of the method on the
Librispeech corpus, which consists of read ction books, and we discuss it's
behaviour qualitatively.
@inproceedings{BUT160005,
author="BENEŠ, K. and IRIE, K. and BECK, E. and SCHLÜTER, R. and NEY, H.",
title="Unsupervised Language Model Adaptation for Speech Recognition with no Extra Resources",
booktitle="Proceedings of DAGA 2019",
year="2019",
pages="954--957",
publisher="DEGA Head office, Deutsche Gesellschaft für Akustik",
address="Rostock",
isbn="978-3-939296-14-0",
url="https://www.dega-akustik.de/publikationen/online-proceedings/"
}