Large Language Model Based Generative Error Correction: A Challenge and Baselines for Speech Recognition, Speaker Tagging, and Emotion Recognition
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914175222022144 |
|---|---|
| author | Yang, Chao-Han Huck Park, Taejin Gong, Yuan Li, Yuanchao Chen, Zhehuai Lin, Yen-Ting Chen, Chen Hu, Yuchen Dhawan, Kunal Żelasko, Piotr Zhang, Chao Chen, Yun-Nung Tsao, Yu Balam, Jagadeesh Ginsburg, Boris Siniscalchi, Sabato Marco Chng, Eng Siong Bell, Peter Lai, Catherine Watanabe, Shinji Stolcke, Andreas |
| author_facet | Yang, Chao-Han Huck Park, Taejin Gong, Yuan Li, Yuanchao Chen, Zhehuai Lin, Yen-Ting Chen, Chen Hu, Yuchen Dhawan, Kunal Żelasko, Piotr Zhang, Chao Chen, Yun-Nung Tsao, Yu Balam, Jagadeesh Ginsburg, Boris Siniscalchi, Sabato Marco Chng, Eng Siong Bell, Peter Lai, Catherine Watanabe, Shinji Stolcke, Andreas |
| contents | Given recent advances in generative AI technology, a key question is how large language models (LLMs) can enhance acoustic modeling tasks using text decoding results from a frozen, pretrained automatic speech recognition (ASR) model. To explore new capabilities in language modeling for speech processing, we introduce the generative speech transcription error correction (GenSEC) challenge. This challenge comprises three post-ASR language modeling tasks: (i) post-ASR transcription correction, (ii) speaker tagging, and (iii) emotion recognition. These tasks aim to emulate future LLM-based agents handling voice-based interfaces while remaining accessible to a broad audience by utilizing open pretrained language models or agent-based APIs. We also discuss insights from baseline evaluations, as well as lessons learned for designing future evaluations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_09785 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Large Language Model Based Generative Error Correction: A Challenge and Baselines for Speech Recognition, Speaker Tagging, and Emotion Recognition Yang, Chao-Han Huck Park, Taejin Gong, Yuan Li, Yuanchao Chen, Zhehuai Lin, Yen-Ting Chen, Chen Hu, Yuchen Dhawan, Kunal Żelasko, Piotr Zhang, Chao Chen, Yun-Nung Tsao, Yu Balam, Jagadeesh Ginsburg, Boris Siniscalchi, Sabato Marco Chng, Eng Siong Bell, Peter Lai, Catherine Watanabe, Shinji Stolcke, Andreas Computation and Language Artificial Intelligence Machine Learning Sound Audio and Speech Processing Given recent advances in generative AI technology, a key question is how large language models (LLMs) can enhance acoustic modeling tasks using text decoding results from a frozen, pretrained automatic speech recognition (ASR) model. To explore new capabilities in language modeling for speech processing, we introduce the generative speech transcription error correction (GenSEC) challenge. This challenge comprises three post-ASR language modeling tasks: (i) post-ASR transcription correction, (ii) speaker tagging, and (iii) emotion recognition. These tasks aim to emulate future LLM-based agents handling voice-based interfaces while remaining accessible to a broad audience by utilizing open pretrained language models or agent-based APIs. We also discuss insights from baseline evaluations, as well as lessons learned for designing future evaluations. |
| title | Large Language Model Based Generative Error Correction: A Challenge and Baselines for Speech Recognition, Speaker Tagging, and Emotion Recognition |
| topic | Computation and Language Artificial Intelligence Machine Learning Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2409.09785 |