LMAC-TD: Producing Time Domain Explanations for Audio Classifiers
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_ | 1866910602519117824 |
|---|---|
| author | Mancini, Eleonora Paissan, Francesco Ravanelli, Mirco Subakan, Cem |
| author_facet | Mancini, Eleonora Paissan, Francesco Ravanelli, Mirco Subakan, Cem |
| contents | Neural networks are typically black-boxes that remain opaque with regards to their decision mechanisms. Several works in the literature have proposed post-hoc explanation methods to alleviate this issue. This paper proposes LMAC-TD, a post-hoc explanation method that trains a decoder to produce explanations directly in the time domain. This methodology builds upon the foundation of L-MAC, Listenable Maps for Audio Classifiers, a method that produces faithful and listenable explanations. We incorporate SepFormer, a popular transformer-based time-domain source separation architecture. We show through a user study that LMAC-TD significantly improves the audio quality of the produced explanations while not sacrificing from faithfulness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_08655 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LMAC-TD: Producing Time Domain Explanations for Audio Classifiers Mancini, Eleonora Paissan, Francesco Ravanelli, Mirco Subakan, Cem Sound Artificial Intelligence Machine Learning Audio and Speech Processing Signal Processing Neural networks are typically black-boxes that remain opaque with regards to their decision mechanisms. Several works in the literature have proposed post-hoc explanation methods to alleviate this issue. This paper proposes LMAC-TD, a post-hoc explanation method that trains a decoder to produce explanations directly in the time domain. This methodology builds upon the foundation of L-MAC, Listenable Maps for Audio Classifiers, a method that produces faithful and listenable explanations. We incorporate SepFormer, a popular transformer-based time-domain source separation architecture. We show through a user study that LMAC-TD significantly improves the audio quality of the produced explanations while not sacrificing from faithfulness. |
| title | LMAC-TD: Producing Time Domain Explanations for Audio Classifiers |
| topic | Sound Artificial Intelligence Machine Learning Audio and Speech Processing Signal Processing |
| url | https://arxiv.org/abs/2409.08655 |