Integrated Method of Deep learning and Large Language Model in Speech Recognition
Preprint
- 11 August 2024
- preprint
- Published by MDPI AG in Preprints.org
Abstract
This research aims to explore the integration method of deep learning and large language models in speech recognition to improve the system’s recognition accuracy and ability to handle complex contexts. Deep neural network (DNN), convolutional neural network (CNN), long short-term memory network (LSTM) and Transformer-based large language model are used to build an integrated acoustic and language model framework. Experiments on TIMIT, LibriSpeech and Common Voice datasets show that the ensemble model shows significant improvements in both word error rate (WER) and real-time factor (RTF) compared to traditional models. Especially in terms of adaptability to multiple languages and accent changes, the model shows superior performance. The conclusion shows that through technology integration, the performance of the speech recognition system in complex environments can be effectively improved, providing a new direction for the future development of speech recognition technology.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- MuseChat: A Conversational Music Recommendation System for Videos2024
- Chain-of-Interaction: Enhancing Large Language Models for Psychiatric Behavior Understanding by Dyadic Contexts2024
- Adapting LLMs for Efficient Context Processing through Soft Prompt Compression2024
- MM-SOC: Benchmarking Multimodal Large Language Models in Social Media Platforms2024
- Visual In-Context Learning for Large Vision-Language Models2024
- ImplicitAVE: An Open-Source Dataset and Multimodal LLMs Benchmark for Implicit Attribute Value Extraction2024
- Length-Aware Multi-Kernel Transformer for Long Document Classification2024
- Enhancing Document-level Event Argument Extraction with Contextual Clues and Role Relevance2023
- TeamShakespeare at SemEval-2023 Task 6: Understand Legal Documents with Contextualized Large Language Models2023
- Remaining Useful Life Assessment for Lithium-Ion Batteries Using CNN-LSTM-DNN Hybrid MethodIEEE Transactions on Vehicular Technology, 2021