Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2409.17044 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915318933225472 |
|---|---|
| author | Verdini, Francesco Melucci, Pierfrancesco Perna, Stefano Cariaggi, Francesco Gaido, Marco Papi, Sara Mazurek, Szymon Kasztelnik, Marek Bentivogli, Luisa Bratières, Sébastien Merialdo, Paolo Scardapane, Simone |
| author_facet | Verdini, Francesco Melucci, Pierfrancesco Perna, Stefano Cariaggi, Francesco Gaido, Marco Papi, Sara Mazurek, Szymon Kasztelnik, Marek Bentivogli, Luisa Bratières, Sébastien Merialdo, Paolo Scardapane, Simone |
| contents | The remarkable performance achieved by Large Language Models (LLM) has driven research efforts to leverage them for a wide range of tasks and input modalities. In speech-to-text (S2T) tasks, the emerging solution consists of projecting the output of the encoder of a Speech Foundational Model (SFM) into the LLM embedding space through an adapter module. However, no work has yet investigated how much the downstream-task performance depends on each component (SFM, adapter, LLM) nor whether the best design of the adapter depends on the chosen SFM and LLM. To fill this gap, we evaluate the combination of 5 adapter modules, 2 LLMs (Mistral and Llama), and 2 SFMs (Whisper and SeamlessM4T) on two widespread S2T tasks, namely Automatic Speech Recognition and Speech Translation. Our results demonstrate that the SFM plays a pivotal role in downstream performance, while the adapter choice has moderate impact and depends on the SFM and LLM. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_17044 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | How to Connect Speech Foundation Models and Large Language Models? What Matters and What Does Not Verdini, Francesco Melucci, Pierfrancesco Perna, Stefano Cariaggi, Francesco Gaido, Marco Papi, Sara Mazurek, Szymon Kasztelnik, Marek Bentivogli, Luisa Bratières, Sébastien Merialdo, Paolo Scardapane, Simone Computation and Language Artificial Intelligence Machine Learning The remarkable performance achieved by Large Language Models (LLM) has driven research efforts to leverage them for a wide range of tasks and input modalities. In speech-to-text (S2T) tasks, the emerging solution consists of projecting the output of the encoder of a Speech Foundational Model (SFM) into the LLM embedding space through an adapter module. However, no work has yet investigated how much the downstream-task performance depends on each component (SFM, adapter, LLM) nor whether the best design of the adapter depends on the chosen SFM and LLM. To fill this gap, we evaluate the combination of 5 adapter modules, 2 LLMs (Mistral and Llama), and 2 SFMs (Whisper and SeamlessM4T) on two widespread S2T tasks, namely Automatic Speech Recognition and Speech Translation. Our results demonstrate that the SFM plays a pivotal role in downstream performance, while the adapter choice has moderate impact and depends on the SFM and LLM. |
| title | How to Connect Speech Foundation Models and Large Language Models? What Matters and What Does Not |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2409.17044 |