Contextual Speech Recognition With Difficult Negative Training Examples

Abstract

Improving the representation of contextual information is key to unlocking the potential of end-to-end (E2E) automatic speech recognition (ASR). In this work, we present a novel and simple approach for training an ASR context mechanism with difficult negative examples. The main idea is to focus on proper nouns (e.g., unique entities such as names of people and places) in the reference transcript, and use phonetically similar phrases as negative examples, encouraging the neural model to learn more discriminative representations. We apply our approach to an end-to-end contextual ASR model that jointly learns to transcribe and select the correct context items, and show that our proposed method gives up to \(53.1%\) relative improvement in word error rate (WER) across several benchmarks.

Stats

• citations22
• S2 citations—
• github stars0
• HF likes0
• heat score10.21
• arxiv keyalon2018contextual

Related papers

• Robust Acoustic And Semantic Contextual Biasing In Neural Transducers For Speech Recognition (2023)8.60
• Improving Neural Biasing For Contextual Speech Recognition By Early Context Injection And Text Perturbation (2024)8.09
• Contextual Adapters For Personalized Speech Recognition In Neural Transducers (2022)12.47
• Improving RNN-T ASR Accuracy Using Context Audio (2020)5.84
• Contextualized End-to-end Speech Recognition With Contextual Phrase Prediction Network (2023)10.48
• Contextualized End-to-end Automatic Speech Recognition With Intermediate Biasing Loss (2024)5.84
• Contextualized Streaming End-to-end Speech Recognition With Trie-based Deep Biasing And Shallow Fusion (2021)13.44
• Deep Context: End-to-end Contextual Speech Recognition (2018)15.57