Memory Augmented Lookup Dictionary Based Language Modeling For Automatic Speech Recognition
2022 · Yukun Feng, Ming Tu, Rui Xia, et al.
Abstract
Recent studies have shown that using an external Language Model (LM) benefits the end-to-end Automatic Speech Recognition (ASR). However, predicting tokens that appear less frequently in the training set is still quite challenging. The long-tail prediction problems have been widely studied in many applications, but only been addressed by a few studies for ASR and LMs. In this paper, we propose a new memory augmented lookup dictionary based Transformer architecture for LM. The newly introduced lookup dictionary incorporates rich contextual information in training set, which is vital to correctly predict long-tail tokens. With intensive experiments on Chinese and English data sets, our proposed method is proved to outperform the baseline Transformer LM by a great margin on both word/character error rate and tail tokens error rate. This is achieved without impact on the decoding efficiency. Overall, we demonstrate the effectiveness of our proposed method in boosting the ASR decoding perfo
Authors
(none)
Tags
Stats
Related papers
- Transformer Language Models With Lstm-based Cross-utterance Information Representation (2021)10.48
- Multilingual And Fully Non-autoregressive ASR With Large Language Model Fusion: A Comprehensive Study (2024)0.00
- Multi-task Language Modeling For Improving Speech Recognition Of Rare Words (2020)8.35
- Attention-based Contextual Language Model Adaptation For Speech Recognition (2021)0.00
- Transducer-llama: Integrating Llms Into Streamable Transducer-based Speech Recognition (2024)3.58
- Harnessing The Zero-shot Power Of Instruction-tuned Large Language Model In End-to-end Speech Recognition (2023)0.00
- Transfer Learning Of Language-independent End-to-end ASR With Language Model Fusion (2018)0.00
- Delayed Fusion: Integrating Large Language Models Into First-pass Decoding In End-to-end Speech Recognition (2025)5.84