Picture for Benjamin Elizalde

Benjamin Elizalde

Microsoft

PAM: Prompting Audio-Language Models for Audio Quality Assessment

Add code
Feb 01, 2024
Viaarxiv icon

Prompting Audios Using Acoustic Properties For Emotion Representation

Oct 05, 2023
Figure 1 for Prompting Audios Using Acoustic Properties For Emotion Representation
Figure 2 for Prompting Audios Using Acoustic Properties For Emotion Representation
Figure 3 for Prompting Audios Using Acoustic Properties For Emotion Representation
Figure 4 for Prompting Audios Using Acoustic Properties For Emotion Representation
Viaarxiv icon

Training Audio Captioning Models without Audio

Add code
Sep 14, 2023
Figure 1 for Training Audio Captioning Models without Audio
Figure 2 for Training Audio Captioning Models without Audio
Figure 3 for Training Audio Captioning Models without Audio
Figure 4 for Training Audio Captioning Models without Audio
Viaarxiv icon

Natural Language Supervision for General-Purpose Audio Representations

Add code
Sep 11, 2023
Viaarxiv icon

Pengi: An Audio Language Model for Audio Tasks

Add code
May 19, 2023
Figure 1 for Pengi: An Audio Language Model for Audio Tasks
Figure 2 for Pengi: An Audio Language Model for Audio Tasks
Figure 3 for Pengi: An Audio Language Model for Audio Tasks
Figure 4 for Pengi: An Audio Language Model for Audio Tasks
Viaarxiv icon

Synergy between human and machine approaches to sound/scene recognition and processing: An overview of ICASSP special session

Feb 24, 2023
Viaarxiv icon

Describing emotions with acoustic property prompts for speech emotion recognition

Nov 14, 2022
Figure 1 for Describing emotions with acoustic property prompts for speech emotion recognition
Figure 2 for Describing emotions with acoustic property prompts for speech emotion recognition
Figure 3 for Describing emotions with acoustic property prompts for speech emotion recognition
Figure 4 for Describing emotions with acoustic property prompts for speech emotion recognition
Viaarxiv icon

Audio Retrieval with WavText5K and CLAP Training

Add code
Sep 28, 2022
Figure 1 for Audio Retrieval with WavText5K and CLAP Training
Figure 2 for Audio Retrieval with WavText5K and CLAP Training
Figure 3 for Audio Retrieval with WavText5K and CLAP Training
Figure 4 for Audio Retrieval with WavText5K and CLAP Training
Viaarxiv icon

CLAP: Learning Audio Concepts From Natural Language Supervision

Jun 09, 2022
Figure 1 for CLAP: Learning Audio Concepts From Natural Language Supervision
Figure 2 for CLAP: Learning Audio Concepts From Natural Language Supervision
Figure 3 for CLAP: Learning Audio Concepts From Natural Language Supervision
Figure 4 for CLAP: Learning Audio Concepts From Natural Language Supervision
Viaarxiv icon

COVID-19 Detection Using Recorded Coughs in the 2021 DiCOVA Challenge

May 22, 2021
Figure 1 for COVID-19 Detection Using Recorded Coughs in the 2021 DiCOVA Challenge
Figure 2 for COVID-19 Detection Using Recorded Coughs in the 2021 DiCOVA Challenge
Figure 3 for COVID-19 Detection Using Recorded Coughs in the 2021 DiCOVA Challenge
Figure 4 for COVID-19 Detection Using Recorded Coughs in the 2021 DiCOVA Challenge
Viaarxiv icon