Improving Contextual Recognition of Rare Words with an Alternate Spelling Prediction Model
This addresses a specific bottleneck in ASR for handling rare words, but is incremental as it builds on prior similar methods with a simpler implementation.
The paper tackled the problem of end-to-end ASR models struggling with rare and out-of-vocabulary words by proposing an alternate spelling prediction model, which improved recall of rare words by 34.7% and out-of-vocabulary words by 97.2% relative to baseline contextual biasing.
Contextual ASR, which takes a list of bias terms as input along with audio, has drawn recent interest as ASR use becomes more widespread. We are releasing contextual biasing lists to accompany the Earnings21 dataset, creating a public benchmark for this task. We present baseline results on this benchmark using a pretrained end-to-end ASR model from the WeNet toolkit. We show results for shallow fusion contextual biasing applied to two different decoding algorithms. Our baseline results confirm observations that end-to-end models struggle in particular with words that are rarely or never seen during training, and that existing shallow fusion techniques do not adequately address this problem. We propose an alternate spelling prediction model that improves recall of rare words by 34.7% relative and of out-of-vocabulary words by 97.2% relative, compared to contextual biasing without alternate spellings. This model is conceptually similar to ones used in prior work, but is simpler to implement as it does not rely on either a pronunciation dictionary or an existing text-to-speech system.