Dealing with Newly Emerging OOVs in Broadcast Programs by Daily Updates of the Lexicon and Language Model

This paper deals with out-of-vocabulary (OOV) word recognition in the task of 24/7 broadcast stream transcription. Here, the majority of OOVs newly emerging over time are constituted of names of politicians, athletes, major world events, disasters, etc. The absence of these content OOVs, e.g. COVID-19, is detrimental to human understanding of the recognized text and harmful to further NLP processing, such as machine translation, named entity recognition or any type of semantic or dialogue analysis. In production environments, content OOVs are of extreme importance and it is essential that their correct transcription is provided as soon as possible. For this purpose, an approach based on daily updates of the lexicon and language model is proposed. It consists of three consecutive steps: a) the identification of new content OOVs from already existing text sources, b) their controlled addition into the lexicon of the transcription system and c) proper tuning of the language model. Experimental evaluation is performed on an extensive data-set compiled from various Czech broadcast programs. This data was produced by a real transcription platform over the course of 300 days in 2019. Detailed statistics and analysis of new content OOVs emerging within this period are also provided.

[1]  Florian Metze,et al.  Subword and Crossword Units for CTC Acoustic Models , 2017, INTERSPEECH.

[2]  Hui Lin,et al.  OOV detection by joint word/phone lattice alignment , 2007, 2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU).

[3]  Philip Gage,et al.  A new algorithm for data compression , 1994 .

[4]  Tatsuya Kawahara,et al.  Improving OOV Detection and Resolution with External Language Models in Acoustic-to-Word ASR , 2018, 2018 IEEE Spoken Language Technology Workshop (SLT).

[5]  Hynek Hermansky,et al.  Combination of strongly and weakly constrained recognizers for reliable detection of OOVS , 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

[6]  Wei Chu,et al.  Hybrid CTC-Attention based End-to-End Speech Recognition using Subword Units , 2018, 2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP).

[7]  Hermann Ney,et al.  Open vocabulary speech recognition with flat hybrid models , 2005, INTERSPEECH.

[8]  James R. Glass,et al.  Learning units for domain-independent out-of- vocabulary word modelling , 2001, INTERSPEECH.

[9]  Michael Picheny,et al.  Detection and Recovery of OOVs for Improved English Broadcast News Captioning , 2019, INTERSPEECH.

[10]  Dong Yu,et al.  Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition , 2012, IEEE Transactions on Audio, Speech, and Language Processing.

[11]  Bhuvana Ramabhadran,et al.  A new method for OOV detection using hybrid word/fragment system , 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.