Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2410.03904 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917795460022272 |
|---|---|
| author | Raghavan, Ksheeraja Gode, Samiran Shah, Ankit Raghavan, Surabhi Burgard, Wolfram Raj, Bhiksha Singh, Rita |
| author_facet | Raghavan, Ksheeraja Gode, Samiran Shah, Ankit Raghavan, Surabhi Burgard, Wolfram Raj, Bhiksha Singh, Rita |
| contents | We introduce a novel, general-purpose audio generation framework specifically designed for anomaly detection and localization. Unlike existing datasets that predominantly focus on industrial and machine-related sounds, our framework focuses a broader range of environments, particularly useful in real-world scenarios where only audio data are available, such as in video-derived or telephonic audio. To generate such data, we propose a new method inspired by the LLM-Modulo framework, which leverages large language models(LLMs) as world models to simulate such real-world scenarios. This tool is modular allowing a plug-and-play approach. It operates by first using LLMs to predict plausible real-world scenarios. An LLM further extracts the constituent sounds, the order and the way in which these should be merged to create coherent wholes. Much like the LLM-Modulo framework, we include rigorous verification of each output stage, ensuring the reliability of the generated data. The data produced using the framework serves as a benchmark for anomaly detection applications, potentially enhancing the performance of models trained on audio data, particularly in handling out-of-distribution cases. Our contributions thus fill a critical void in audio anomaly detection resources and provide a scalable tool for generating diverse, realistic audio data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_03904 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Did You Hear That? Introducing AADG: A Framework for Generating Benchmark Data in Audio Anomaly Detection Raghavan, Ksheeraja Gode, Samiran Shah, Ankit Raghavan, Surabhi Burgard, Wolfram Raj, Bhiksha Singh, Rita Sound Artificial Intelligence Audio and Speech Processing We introduce a novel, general-purpose audio generation framework specifically designed for anomaly detection and localization. Unlike existing datasets that predominantly focus on industrial and machine-related sounds, our framework focuses a broader range of environments, particularly useful in real-world scenarios where only audio data are available, such as in video-derived or telephonic audio. To generate such data, we propose a new method inspired by the LLM-Modulo framework, which leverages large language models(LLMs) as world models to simulate such real-world scenarios. This tool is modular allowing a plug-and-play approach. It operates by first using LLMs to predict plausible real-world scenarios. An LLM further extracts the constituent sounds, the order and the way in which these should be merged to create coherent wholes. Much like the LLM-Modulo framework, we include rigorous verification of each output stage, ensuring the reliability of the generated data. The data produced using the framework serves as a benchmark for anomaly detection applications, potentially enhancing the performance of models trained on audio data, particularly in handling out-of-distribution cases. Our contributions thus fill a critical void in audio anomaly detection resources and provide a scalable tool for generating diverse, realistic audio data. |
| title | Did You Hear That? Introducing AADG: A Framework for Generating Benchmark Data in Audio Anomaly Detection |
| topic | Sound Artificial Intelligence Audio and Speech Processing |
| url | https://arxiv.org/abs/2410.03904 |