The DOI matches its Crossref record; 15 of the 15 references it cites were found in a registry or an index.
Natural Language Supervision For General-Purpose Audio Representations
Abstract
Audio-Language models jointly learn multimodal text and audio representations that enable Zero-Shot inference. Models rely on the encoders to create powerful representations of the input and generalize to multiple tasks ranging from sounds, music, and speech. Although models have achieved remarkable performance, there is still a gap with task-specific models. In this paper, we propose a Contrastive Language-Audio Pretraining model that is pretrained with a diverse collection of 4.6M audio-text pairs employing two innovative encoders for Zero-Shot inference. To learn audio representations, we trained an audio encoder on 22 audio tasks, instead of the standard training of sound event classification. To learn language representations, we trained an autoregressive decoder-only model instead of the standard encoder-only models. Then, the audio and language representations are brought into a joint multimodal space using Contrastive Learning. We used our encoders to improve the downstream performance by a large margin. We extensively evaluated the generalization of our representations on 26 downstream tasks, the largest in the literature. Our model achieves state of the art results in several tasks outperforming 4 different models and leading the way towards general-purpose audio representations. Code is on GitHub1.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Other research studies align audio modality with text to leverage advancements in LLMs [324]-[326] for various downstream text generation.”
From Retrieval-Augmented Generation for AI-Generated Content: A Survey (2024) · cites this paper as [324]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Audio Set: An ontology and human-labeled dataset for audio events
Gemmeke, J. F., Ellis, D. P. W., Freedman, D., Jansen, A., Lawrence, W., Moore, R. C., Plakal, M., & Ritter, M. (2017) · 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2017.7952261 · Cited by 3,134
Multimodal Language Analysis in the Wild: CMU-MOSEI Dataset and Interpretable Dynamic Fusion Graph
Bagher Zadeh, A., Liang, P. P., Poria, S., Cambria, E., & Morency, L.-P. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1208 · Cited by 1,433 · cited 2×
“The training datasets for the 4.6M collection are: WavCaps [6], Au-dioSet [2], FSD50K [11], Clotho [12], AudioCaps [13], MACS [14], WavText5k [5], SoundDesc [15], NSynth [16], FMA [17], Mosi [18], Meld [19], Iemocap [20], Mosei [21], MSP-Podcast [22], CochlScene [23], LJspeech [24], EpicK-itchen [25], Kinectics700 [26…”
MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations
Poria, S., Hazarika, D., Majumder, N., Naik, G., Cambria, E., & Mihalcea, R. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1050 · Cited by 1,416 · cited 1×
“…are: WavCaps [6], Au-dioSet [2], FSD50K [12], Clotho [13], AudioCaps [14], MACS [15], WavText5k [5], SoundDesc [16], NSynth [17], FMA [18], Mosi [19], Meld [20], Iemocap [21], Mosei [22], MSP-Podcast [23], CochlScene [24], LJspeech [25], EpicK-itchen [26], Kinectics700 [27], findsounds.com.”
FSD50K: An Open Dataset of Human-Labeled Sound Events
Fonseca, E., Favory, X., Pons, J., Font, F., & Serra, X. (2020) · arXiv · doi:10.48550/arxiv.2010.00475 · Cited by 462 · cited 1×
“The training datasets for the 4.6M collection are: WavCaps [6], Au-dioSet [2], FSD50K [12], Clotho [13], AudioCaps [14], MACS [15], WavText5k [5], SoundDesc [16], NSynth [17], FMA [18], Mosi [19], Meld [20], Iemocap [21], Mosei [22], MSP-Podcast [23], CochlScene [24], LJspeech [25], EpicK-itchen…”
MethodWu, Y., Chen, K., Zhang, T., Hui, Y., Berg-Kirkpatrick, T., & Dubnov, S. (2023) · ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp49357.2023.10095969 · Cited by 459 · cited 5×
“We also included the text encoder from CLIP because it was used by different authors [9, 8, 4].”
BackgroundMethodInfluentialCLAP Learning Audio Concepts from Natural Language Supervision
Elizalde, B., Deshmukh, S., Ismail, M. A., & Wang, H. (2023) · ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp49357.2023.10095889 · Cited by 449
Self-citationMOSI: Multimodal Corpus of Sentiment Intensity and Subjectivity Analysis in Online Opinion Videos
Zadeh, A., Zellers, R., Pincus, E., & Morency, L.-P. (2016) · arXiv · doi:10.48550/arxiv.1606.06259 · Cited by 350
A Short Note on the Kinetics-700-2020 Human Action Dataset
Smaira, L., Carreira, J., Noland, E., Clancy, E., Wu, A., & Zisserman, A. (2020) · arXiv · doi:10.48550/arxiv.2010.10864 · Cited by 334
Audioclip: Extending Clip to Image, Text and Audio
Guzhov, A., Raue, F., Hees, J., & Dengel, A. (2022) · ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp43922.2022.9747631 · Cited by 330
HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection
Chen, K., Du, X., Zhu, B., Ma, Z., Berg-Kirkpatrick, T., & Dubnov, S. (2022) · ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp43922.2022.9746312 · Cited by 294
Research works printed but not linked: 11
- 10.21437/Interspeech.2023-1136 · DOI
- 10.1109/ICASSP43922.2022.9747669 · DOI · Paper page
- 10.1109/TASLP.2021.3133208 · DOI · Paper page
- 10.23919/EUSIPCO54536.2021.9616087 · DOI
- 10.1109/TMM.2022.3149712 · DOI
- Engel, Neural audio synthesis of musical notes with wavenet autoencoders
- 10.1007/s10579-008-9076-6 · DOI · Paper page
- 10.1109/TAFFC.2017.2736999 · DOI · Paper page
- 10.23919/APSIPAASC55919.2022.9979822 · DOI
- 10.1007/s11263-021-01531-2 · DOI · Paper page
- 10.1109/ICASSP49357.2023.10096877 · DOI
Cited by
Retrieval-Augmented Generation for AI-Generated Content: A Survey
Zhao, P., Zhang, H., Yu, Q., Wang, Z., Geng, Y., Fu, F., Yang, L., Zhang, W., Jiang, J., & Cui, B. (2024) · arXiv · doi:10.48550/arxiv.2402.19473 · Cited by 240
Metadata
- Authors
- Elizalde, B., Deshmukh, S., & Wang, H.
- Affiliations
- Microsoft
- Venue
- ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- Publisher
- IEEE
- Published
- 2024-04-14
- Pages
- 336-340
- Cited by
- 69
- References
- 15
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Natural Language Supervision For General-Purpose Audio Representations. https://app.cochat.ai/papers/10.1109/icassp48485.2024.10448504
- The paper
- Elizalde, B., Deshmukh, S., & Wang, H. (2024). Natural Language Supervision For General-Purpose Audio Representations. ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https://doi.org/10.1109/icassp48485.2024.10448504
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.