Spectrogram features for audio and speech analysis
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914396249260032 |
|---|---|
| author | McLoughlin, Ian Pham, Lam Song, Yan Miao, Xiaoxiao Phan, Huy Cai, Pengfei Gu, Qing Nan, Jiang Song, Haoyu Soh, Donny |
| author_facet | McLoughlin, Ian Pham, Lam Song, Yan Miao, Xiaoxiao Phan, Huy Cai, Pengfei Gu, Qing Nan, Jiang Song, Haoyu Soh, Donny |
| contents | Spectrogram-based representations have grown to dominate the feature space for deep learning audio analysis systems, and are often adopted for speech analysis also. Initially, the primary motivator for spectrogram-based representations was their ability to present sound as a two dimensional signal in the time-frequency plane, which not only provides an interpretable physical basis for analysing sound, but also unlocks the use of a wide range of machine learning techniques such as convolutional neural networks, that had been developed for image processing. A spectrogram is a matrix characterised by the resolution and span of its two dimensions, as well as by the representation and scaling of each element. Many possibilities for these three characteristics have been explored by researchers across numerous application areas, with different settings showing affinity for various tasks. This paper reviews the use of spectrogram-based representations and surveys the state-of-the-art to question how front-end feature representation choice allies with back-end classifier architecture for different tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_14917 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Spectrogram features for audio and speech analysis McLoughlin, Ian Pham, Lam Song, Yan Miao, Xiaoxiao Phan, Huy Cai, Pengfei Gu, Qing Nan, Jiang Song, Haoyu Soh, Donny Audio and Speech Processing Artificial Intelligence Machine Learning Signal Processing Spectrogram-based representations have grown to dominate the feature space for deep learning audio analysis systems, and are often adopted for speech analysis also. Initially, the primary motivator for spectrogram-based representations was their ability to present sound as a two dimensional signal in the time-frequency plane, which not only provides an interpretable physical basis for analysing sound, but also unlocks the use of a wide range of machine learning techniques such as convolutional neural networks, that had been developed for image processing. A spectrogram is a matrix characterised by the resolution and span of its two dimensions, as well as by the representation and scaling of each element. Many possibilities for these three characteristics have been explored by researchers across numerous application areas, with different settings showing affinity for various tasks. This paper reviews the use of spectrogram-based representations and surveys the state-of-the-art to question how front-end feature representation choice allies with back-end classifier architecture for different tasks. |
| title | Spectrogram features for audio and speech analysis |
| topic | Audio and Speech Processing Artificial Intelligence Machine Learning Signal Processing |
| url | https://arxiv.org/abs/2603.14917 |