DCASE Workshop 2021, ID 51 - Continual Learning for Automated Audio Captioning Using the Learning...

preview_player
Показать описание
Continual Learning for Automated Audio Captioning Using the Learning without Forgetting Approach

Jan Berg (Tampere University); Konstantinos Drossos (Tampere University)

  1. DCASE Workshop
Рекомендации по теме
DCASE Workshop 2021, 0:07:49

DCASE Workshop 2021, ID 51 - Continual Learning for Automated Audio Captioning Using the Learning...

DCASE 2020 Workshop, 0:10:06

DCASE 2020 Workshop, ID 51, Diego de Benito-Gorron et al.

DCASE Workshop 2021, 0:05:25

DCASE Workshop 2021, ID 26 - Multiple Feature Resolutions for Different Polyphonic Sound Detectio...

DCASE Workshop 2021, 0:08:09

DCASE Workshop 2021, ID 31 - Acoustic Event Detection Using Speaker Recognition Techniques: Model...

DCASE Workshop 2021, 0:07:07

DCASE Workshop 2021, ID 9 - Automated Audio Captioning with Weakly Supervised Pre-Training and Wo...

DCASE 2020 Workshop, 0:03:00

DCASE 2020 Workshop, Challenge Spotlight, Task 4

P51Mustang acoustic Event 0:00:16

P51Mustang acoustic Event detection

Event Specific Attention 0:03:20

Event Specific Attention for Polyphonic Sound Event Detection - (3 minutes introduction)

MARVEL Assets Demo 0:03:23

MARVEL Assets Demo Series - Automated Audio Captioning (AAC) Demo

Deep Learning for 0:35:07

Deep Learning for Automated Audio Captioning, Wenwu Wang @ University of Surrey | GHOST Day 2022

Using various pre-trained 0:03:18

Using various pre-trained modelsfor audio feature extractionin automated audio captioning

E Zamora - 0:11:26

E Zamora - 180B A09 Eco Acoustic Event Detection Remote Sensing

Object & Scene 0:01:51

Object & Scene Recognition (EN)

Meet Mira Rizkallah 0:08:51

Meet Mira Rizkallah and Vincent Lostanlen, 2 young but well-travelled researchers at Centrale Nantes

Singapore Invents Noise-Cancelling 0:01:31

Singapore Invents Noise-Cancelling Headphones for Flats

New City/Back of 1:01:32

New City/Back of the Yards January Roundtable

[ISPL seminar]SSAST: Self-Supervised 1:02:42

[ISPL seminar]SSAST: Self-Supervised Audio Spectrogram Transformer

text to speech 0:04:51

text to speech

tinyML Talks: Industry 0:56:45

tinyML Talks: Industry 4.0: Predictive Maintenance using Arduino Portenta H7 and Edge Impulse

Información y computación 1:02:04

Información y computación cuánticas - Dr. Guillermo Cordourier

Reinhold Haeb Umbach 0:51:56

Reinhold Haeb Umbach 'Far-Field Speech Recognition'

PR-314: VATT: Transformers 0:53:43

PR-314: VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio, and Text

Tìm hiểu encoder 0:51:56

Tìm hiểu encoder trong Transformer