Unsupervised Language Model Adaptation by Data Selection for Speech Recognition

Khassanov, Yerbolat; Chong, Tze Yuang; Bigot, Benjamin; Chng, Eng Siong

doi:10.1007/978-3-319-54472-4_48

Cited by 4 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This approach will retain the linguistic regularities encapsulated within original pre-trained NLM, given that embeddings of the rare words are properly modified. Our method can be also viewed as a language model adaptation task [25] where instead of topic or speaking style the vocabulary is adapted to conform with the words used in the target domain.…”

Section: Embedding Matrix Augmentationmentioning

confidence: 99%

Enriching Rare Word Representations in Neural Language Models by Embedding Matrix Augmentation

et al. 2019

Self Cite

View full text Add to dashboard Cite

The neural language models (NLM) achieve strong generalization capability by learning the dense representation of words and using them to estimate probability distribution function. However, learning the representation of rare words is a challenging problem causing the NLM to produce unreliable probability estimates. To address this problem, we propose a method to enrich representations of rare words in pre-trained NLM and consequently improve its probability estimation performance. The proposed method augments the word embedding matrices of pre-trained NLM while keeping other parameters unchanged. Specifically, our method updates the embedding vectors of rare words using embedding vectors of other semantically and syntactically similar words. To evaluate the proposed method, we enrich the rare street names in the pre-trained NLM and use it to rescore 100-best hypotheses output from the Singapore English speech recognition system. The enriched NLM reduces the word error rate by 6% relative and improves the recognition accuracy of the rare words by 16% absolute as compared to the baseline NLM.

show abstract

Section: Embedding Matrix Augmentationmentioning

confidence: 99%

Enriching Rare Word Representations in Neural Language Models by Embedding Matrix Augmentation

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…This is due to the 'locked-in' phenomenon, also referred to as error propagation, where increasing the probabilities of misrecognized words imposes the ASR system to repeat the same mistakes. To mitigate the 'locked-in' phenomenon, Khassanov et al [107] proposed to use cache data to select relevant sentences from the generic background corpus, and then to use selected data to update the background LM. Although the proposed method avoids the direct usage of cache data, it will increase the latency and introduce additional complexities such as reliable data selection process.…”

Section: )mentioning

confidence: 99%