DeepAI AI Chat
Log In Sign Up

Improving Contextual Recognition of Rare Words with an Alternate Spelling Prediction Model

by   Jennifer Drexler Fox, et al.

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 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.


page 1

page 2

page 3

page 4


Contextual Adapters for Personalized Speech Recognition in Neural Transducers

Personal rare word recognition in end-to-end Automatic Speech Recognitio...

Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion

How to leverage dynamic contextual information in end-to-end speech reco...

Context-Aware Transformer Transducer for Speech Recognition

End-to-end (E2E) automatic speech recognition (ASR) systems often have d...

Contextual RNN-T For Open Domain ASR

End-to-end (E2E) systems for automatic speech recognition (ASR), such as...

Improving Rare Word Recognition with LM-aware MWER Training

Language models (LMs) significantly improve the recognition accuracy of ...

Tree-constrained Pointer Generator with Graph Neural Network Encodings for Contextual Speech Recognition

Incorporating biasing words obtained as contextual knowledge is critical...

Contextual Density Ratio for Language Model Biasing of Sequence to Sequence ASR Systems

End-2-end (E2E) models have become increasingly popular in some ASR task...