Multi-resolution conformer for sound event detection: Analysis and optimization
The Conformer architecture has achieved state-of-the-art results in several tasks, including automatic speech recognition and automatic speaker verification. However, its utilization in sound event detec tion and in particular in the DCASE Challenge Task 4 has been limited despite winning the 2020 e...
| Autores: | , , , , |
|---|---|
| Tipo de recurso: | capítulo de libro |
| Fecha de publicación: | 2023 |
| País: | España |
| Institución: | Universidad Autónoma de Madrid |
| Repositorio: | Biblos-e Archivo. Repositorio Institucional de la UAM |
| Idioma: | inglés |
| OAI Identifier: | oai:repositorio.uam.es:10486/719735 |
| Acceso en línea: | http://hdl.handle.net/10486/719735 |
| Access Level: | acceso abierto |
| Palabra clave: | DCASE 2023 sound event detection conformer Telecomunicaciones |
| Sumario: | The Conformer architecture has achieved state-of-the-art results in several tasks, including automatic speech recognition and automatic speaker verification. However, its utilization in sound event detec tion and in particular in the DCASE Challenge Task 4 has been limited despite winning the 2020 edition. Although the Conformer architecture may not excel in accurately localizing sound events, it shows promising potential in minimizing confusion between differ ent classes. Therefore, in this paper we propose a Conformer opti mization to enhance the second Polyphonic Sound Detection Score (PSDS) scenario defined for the DCASE 2023 Task 4A. With the aim of maximizing its classification properties, we have employed recently proposed methods such as Frequency Dynamic Convolu tions in addition to our multi-resolution approach, which allow us to analyse its behaviour over different time-frequency resolution points. Furthermore, our Conformer systems are compared with multi-resolution models based on Convolutional Recurrent Neural Networks (CRNNs) to evaluate the respective benefits of each ar chitecture in relation to the two proposed scenarios for the PSDS and the different time-frequency resolution points defined. These systems were submitted as our participation in the DCASE 2023 Task 4A, in which our Conformer system obtained a PSDS2 value of 0.728, achieving one of the highest scores for this scenario among systems trained without external resources |
|---|