Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2407.21414 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916408092262400 |
|---|---|
| author | Naderi, Maryam Hermann, Enno Nanchen, Alexandre Hovsepyan, Sevada -Doss, Mathew Magimai. |
| author_facet | Naderi, Maryam Hermann, Enno Nanchen, Alexandre Hovsepyan, Sevada -Doss, Mathew Magimai. |
| contents | As large language models (LLMs) grow in parameter size and capabilities, such as interaction through prompting, they open up new ways of interfacing with automatic speech recognition (ASR) systems beyond rescoring n-best lists. This work investigates post-hoc correction of ASR transcripts with LLMs. To avoid introducing errors into likely accurate transcripts, we propose a range of confidence-based filtering methods. Our results indicate that this can improve the performance of less competitive ASR systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_21414 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards interfacing large language models with ASR systems using confidence measures and prompting Naderi, Maryam Hermann, Enno Nanchen, Alexandre Hovsepyan, Sevada -Doss, Mathew Magimai. Audio and Speech Processing Computation and Language As large language models (LLMs) grow in parameter size and capabilities, such as interaction through prompting, they open up new ways of interfacing with automatic speech recognition (ASR) systems beyond rescoring n-best lists. This work investigates post-hoc correction of ASR transcripts with LLMs. To avoid introducing errors into likely accurate transcripts, we propose a range of confidence-based filtering methods. Our results indicate that this can improve the performance of less competitive ASR systems. |
| title | Towards interfacing large language models with ASR systems using confidence measures and prompting |
| topic | Audio and Speech Processing Computation and Language |
| url | https://arxiv.org/abs/2407.21414 |