Publication Details
Contextual Biasing Methods for Improving Rare Word Detection in Automatic Speech Recognition
NIGMATULINA, I.
Prasad Amrutha (DCGM)
RANGAPPA, P.
Madikeri Srikanth
Motlíček Petr, doc. Ing., Ph.D. (DCGM)
HELMKE, H.
KLEINERT, M.
Automatic speech recognition, air traffic control, domain adaptation, contextual
biasing, rare word recognition
In specialized domains like Air Traffic Control (ATC), a notable challenge in
porting a deployed Automatic Speech Recognition (ASR) system from one airport to
another is the alteration in the set of crucial words that must be ac- curately
detected in the new environment. Typically, such words have limited occurrences
in training data, making it impractical to retrain the ASR system. This paper
explores innovative word-boosting techniques to improve the detec- tion rate of
such rare words in the ASR hypotheses for the ATC domain. Two acoustic models are
investigated: a hybrid CNN-TDNNF model trained from scratch and a pre-trained
wav2vec2-based XLSR model fine-tuned on a common ATC dataset. The word boosting
is done in three ways. First, an out-of-vocabulary word addition method is
explored. Second, G-boosting is explored, which amends the language model before
building the decoding graph. Third, the boosting is performed on the fly during
decoding using lattice re-scoring. The results indicate that the G-boosting
method performs best and provides an approximately 30-43% relative improvement in
recall of the boosted words. Moreover, a relative improve- ment of up to 48% is
obtained upon combining G-boosting and lattice-rescoring
@inproceedings{BUT193355,
author="BHATTACHARJEE, M. and NIGMATULINA, I. and PRASAD, A. and RANGAPPA, P. and MADIKERI, S. and MOTLÍČEK, P. and HELMKE, H. and KLEINERT, M.",
title="Contextual Biasing Methods for Improving Rare Word Detection in Automatic Speech Recognition",
booktitle="ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
year="2024",
pages="12652--12656",
publisher="IEEE Signal Processing Society",
address="Seoul",
doi="10.1109/ICASSP48485.2024.10447465",
isbn="979-8-3503-4485-1",
url="https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10447465"
}