Minimising Biasing Word Errors For Contextual ASR With The Tree-constrained Pointer Generator
2022 · Guangzhi Sun, Chao Zhang, Philip C Woodland
Abstract
Contextual knowledge is essential for reducing speech recognition errors on high-valued long-tail words. This paper proposes a novel tree-constrained pointer generator (TCPGen) component that enables end-to-end ASR models to bias towards a list of long-tail words obtained using external contextual information. With only a small overhead in memory use and computation cost, TCPGen can structure thousands of biasing words efficiently into a symbolic prefix-tree and creates a neural shortcut between the tree and the final ASR output to facilitate the recognition of the biasing words. To enhance TCPGen, we further propose a novel minimum biasing word error (MBWE) loss that directly optimises biasing word errors during training, along with a biasing-word-driven language model discounting (BLMD) method during the test. All contextual ASR systems were evaluated on the public Librispeech audiobook corpus and the data from the dialogue state tracking challenges (DSTC) with the biasing lists extr
Authors
(none)
Tags
Stats
Related papers
- Tree-constrained Pointer Generator For End-to-end Contextual Speech Recognition (2021)10.61
- Tree-constrained Pointer Generator With Graph Neural Network Encodings For Contextual Speech Recognition (2022)0.00
- End-to-end Spoken Language Understanding With Tree-constrained Pointer Generator (2022)0.00
- Improving Synthetic Data Training For Contextual Biasing Models With A Keyword-aware Cost Function (2025)0.00
- Improving Neural Biasing For Contextual Speech Recognition By Early Context Injection And Text Perturbation (2024)8.09
- Adaptive Contextual Biasing For Transducer Based Streaming Speech Recognition (2023)7.16
- Fast Context-biasing For CTC And Transducer ASR Models With Ctc-based Word Spotter (2024)2.26
- Towards Contextual Spelling Correction For Customization Of End-to-end Speech Recognition Systems (2022)9.92