CB-Conformer: Contextual biasing Conformer for biased word recognition
This work addresses domain mismatch in speech recognition for biased words, offering incremental improvements in adaptability and inference speed.
The paper tackles the problem of improving automatic speech recognition for biased words in target domains by proposing CB-Conformer, which integrates a Contextual Biasing Module and Self-Adaptive Language Model into Conformer, resulting in a 15.34% character error rate reduction, a 14.13% biased word recall increase, and a 6.80% biased word F1-score increase.
Due to the mismatch between the source and target domains, how to better utilize the biased word information to improve the performance of the automatic speech recognition model in the target domain becomes a hot research topic. Previous approaches either decode with a fixed external language model or introduce a sizeable biasing module, which leads to poor adaptability and slow inference. In this work, we propose CB-Conformer to improve biased word recognition by introducing the Contextual Biasing Module and the Self-Adaptive Language Model to vanilla Conformer. The Contextual Biasing Module combines audio fragments and contextual information, with only 0.2% model parameters of the original Conformer. The Self-Adaptive Language Model modifies the internal weights of biased words based on their recall and precision, resulting in a greater focus on biased words and more successful integration with the automatic speech recognition model than the standard fixed language model. In addition, we construct and release an open-source Mandarin biased-word dataset based on WenetSpeech. Experiments indicate that our proposed method brings a 15.34% character error rate reduction, a 14.13% biased word recall increase, and a 6.80% biased word F1-score increase compared with the base Conformer.