Improving Speech Recognition of Named Entities in Classroom Speech with LLM Revision and Phonetic-Semantic Context
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915943918075904 |
|---|---|
| author | Trinh, Viet Anh He, Xinlu Whitehill, Jacob |
| author_facet | Trinh, Viet Anh He, Xinlu Whitehill, Jacob |
| contents | Classroom speech and lectures often contain named entities (NEs) such as names of people and special terminology. While automatic speech recognition (ASR) systems have achieved remarkable performance on general speech, the word error rate (WER) of state-of-the-art ASR remains high for named entities. Since NE are often the most critical keywords, misrecognizing them can affect all downstream applications, especially when the ASR functions as the front end of a complex system. In this paper, we introduce a large language model (LLM) revision pipeline to revise incorrect NEs in ASR predictions by leveraging not only the LLM's world knowledge and reasoning ability but also the available phonetic and semantic context. We also introduce the NER-MIT-OpenCourseWare dataset, containing 45 hours of data from MIT courses for development and testing. On this dataset, our proposed technique achieves up to 30\% relative WER reduction for NEs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_10779 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Improving Speech Recognition of Named Entities in Classroom Speech with LLM Revision and Phonetic-Semantic Context Trinh, Viet Anh He, Xinlu Whitehill, Jacob Computation and Language Artificial Intelligence Classroom speech and lectures often contain named entities (NEs) such as names of people and special terminology. While automatic speech recognition (ASR) systems have achieved remarkable performance on general speech, the word error rate (WER) of state-of-the-art ASR remains high for named entities. Since NE are often the most critical keywords, misrecognizing them can affect all downstream applications, especially when the ASR functions as the front end of a complex system. In this paper, we introduce a large language model (LLM) revision pipeline to revise incorrect NEs in ASR predictions by leveraging not only the LLM's world knowledge and reasoning ability but also the available phonetic and semantic context. We also introduce the NER-MIT-OpenCourseWare dataset, containing 45 hours of data from MIT courses for development and testing. On this dataset, our proposed technique achieves up to 30\% relative WER reduction for NEs. |
| title | Improving Speech Recognition of Named Entities in Classroom Speech with LLM Revision and Phonetic-Semantic Context |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2506.10779 |