Developing an Effective Training Dataset to Enhance the Performance of AI-based Speaker Separation Systems
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929589566046208 |
|---|---|
| author | Melhem, Rawad Jafar, Assef Dakkak, Oumayma Al |
| author_facet | Melhem, Rawad Jafar, Assef Dakkak, Oumayma Al |
| contents | This paper addresses the challenge of speaker separation, which remains an active research topic despite the promising results achieved in recent years. These results, however, often degrade in real recording conditions due to the presence of noise, echo, and other interferences. This is because neural models are typically trained on synthetic datasets consisting of mixed audio signals and their corresponding ground truths, which are generated using computer software and do not fully represent the complexities of real-world recording scenarios. The lack of realistic training sets for speaker separation remains a major hurdle, as obtaining individual sounds from mixed audio signals is a nontrivial task. To address this issue, we propose a novel method for constructing a realistic training set that includes mixture signals and corresponding ground truths for each speaker. We evaluate this dataset on a deep learning model and compare it to a synthetic dataset. We got a 1.65 dB improvement in Scale Invariant Signal to Distortion Ratio (SI-SDR) for speaker separation accuracy in realistic mixing. Our findings highlight the potential of realistic training sets for enhancing the performance of speaker separation models in real-world scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_08375 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Developing an Effective Training Dataset to Enhance the Performance of AI-based Speaker Separation Systems Melhem, Rawad Jafar, Assef Dakkak, Oumayma Al Sound Artificial Intelligence Audio and Speech Processing This paper addresses the challenge of speaker separation, which remains an active research topic despite the promising results achieved in recent years. These results, however, often degrade in real recording conditions due to the presence of noise, echo, and other interferences. This is because neural models are typically trained on synthetic datasets consisting of mixed audio signals and their corresponding ground truths, which are generated using computer software and do not fully represent the complexities of real-world recording scenarios. The lack of realistic training sets for speaker separation remains a major hurdle, as obtaining individual sounds from mixed audio signals is a nontrivial task. To address this issue, we propose a novel method for constructing a realistic training set that includes mixture signals and corresponding ground truths for each speaker. We evaluate this dataset on a deep learning model and compare it to a synthetic dataset. We got a 1.65 dB improvement in Scale Invariant Signal to Distortion Ratio (SI-SDR) for speaker separation accuracy in realistic mixing. Our findings highlight the potential of realistic training sets for enhancing the performance of speaker separation models in real-world scenarios. |
| title | Developing an Effective Training Dataset to Enhance the Performance of AI-based Speaker Separation Systems |
| topic | Sound Artificial Intelligence Audio and Speech Processing |
| url | https://arxiv.org/abs/2411.08375 |