Enriching Under-represented Named-entities To Improve Speech Recognition Performance

Abstract

Automatic speech recognition (ASR) for under-represented named-entity (UR-NE) is challenging due to such named-entities (NE) have insufficient instances and poor contextual coverage in the training data to learn reliable estimates and representations. In this paper, we propose approaches to enriching UR-NEs to improve speech recognition performance. Specifically, our first priority is to ensure those UR-NEs to appear in the word lattice if there is any. To this end, we make exemplar utterances for those UR-NEs according to their categories (e.g. location, person, organization, etc.), ending up with an improved language model (LM) that boosts the UR-NE occurrence in the word lattice. With more UR-NEs appearing in the lattice, we then boost the recognition performance through lattice rescoring methods. We first enrich the representations of UR-NEs in a pre-trained recurrent neural network LM (RNNLM) by borrowing the embedding representations of the rich-represented NEs (RR-NEs), yielding

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keymao2020enriching

Related papers

• End-to-end Named Entity Extraction From Speech (2018)0.00
• Retraining-free Customized ASR For Enharmonic Words Based On A Named-entity-aware Model And Phoneme Similarity Estimation (2023)4.52
• "i've Heard Of You!": Generate Spoken Named Entity Recognition Data For Unseen Entities (2024)2.26
• On The Use Of External Data For Spoken Named Entity Recognition (2021)6.77
• End-to-end Model For Named Entity Recognition From Speech Without Paired Training Data (2022)6.77
• Whisperner: Unified Open Named Entity And Speech Recognition (2024)2.26
• On The Effectiveness Of Neural Text Generation Based Data Augmentation For Recognition Of Morphologically Rich Speech (2020)0.00
• PROCTER: Pronunciation-aware Contextual Adapter For Personalized Speech Recognition In Neural Transducers (2023)8.60