The DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.
Unified Keyword Spotting and Audio Tagging on Mobile Devices with Transformers
Abstract
Keyword spotting (KWS) is a core human-machine-interaction front-end task for most modern intelligent assistants. Recently, a unified (UniKW-AT) framework has been proposed that adds additional capabilities in the form of audio tagging (AT) to a KWS model. However, previous work did not consider the real-world deployment of a UniKW-AT model, where factors such as model size and inference speed are more important than performance alone. This work introduces three mobile-device deployable models named Unified Transformers (UiT). Our best model achieves an mAP of 34.09 on Audioset, and an accuracy of 97.76 on the public Google Speech Commands V1 dataset. Further, we benchmark our proposed approaches on four mobile platforms, revealing that the proposed UiT models can achieve a speedup of 2 - 6 times against a competitive MobileNetV2.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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
“There are a few recent efforts on joint audio and speech recogntion [7,8,9,10] but none of them exhibit advanced joint reasoning ability.”
From Joint Audio and Speech Understanding (2023) · cites this paper as [7]
Citations
Cites
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2010.11929 · Cited by 47,472
AST: Audio Spectrogram Transformer
Gong, Y., Chung, Y.-A., & Glass, J. (2021) · Interspeech 2021 · doi:10.21437/interspeech.2021-698 · Cited by 1,159
Masked Autoencoders that Listen
Huang, P.-Y., Xu, H., Li, J., Baevski, A., Auli, M., Galuba, W., Metze, F., & Feichtenhofer, C. (2022) · arXiv · doi:10.48550/arxiv.2207.06405 · Cited by 206
Research works printed but not linked: 23
- 10.21437/Interspeech.2021-1428 · DOI
- 10.1109/ICASSP39728.2021.9414777 · DOI
- 10.1109/ICASSP43922.2022.9747025 · DOI
- 10.1109/ACCESS.2021.3078715 · DOI
- 10.1109/ICASSP43922.2022.9747295 · DOI
- 10.21437/Interspeech.2021-1286 · DOI
- 10.1109/TASLP.2021.3073596 · DOI
- 10.21437/Interspeech.2022-607 · DOI
- 10.1109/TASLP.2020.3030497 · DOI · Paper page
- vaswani, 2017, Attention is all you need, Advances in neural information processing systems, 30
- 10.1109/ICASSP.2017.7952261 · DOI · Paper page
- dettmers, 2021, 8-bit optimizers via block-wise quantization, International Conference on Learning Representations
- 10.21437/Interspeech.2019-2680 · DOI · Paper page
- 10.1109/CVPR.2018.00474 · DOI · Paper page
- 10.1109/ICASSP43922.2022.9746431 · DOI
- paszke, 2019, PyTorch: An Imperative Style, High-Performance Deep Learning Library, Advances in Neural IInformation Processing Systems, 8026
- 10.21437/Interspeech.2020-1058 · DOI
- 10.21437/Interspeech.2015-352 · DOI
- 10.21437/Interspeech.2021-383 · DOI
- 10.21437/Interspeech.2022-260 · DOI
- 10.21437/Interspeech.2021-1977 · DOI
- 10.21437/Interspeech.2020-3132 · DOI
- 10.21437/Interspeech.2019-1363 · DOI
Cited by
Sorted by citations
Joint Audio and Speech Understanding
Gong, Y., Liu, A. H., Luo, H., Karlinsky, L., & Glass, J. (2023) · arXiv · doi:10.48550/arxiv.2309.14405 · Cited by 67
“...”
Metadata
- Authors
- Dinkel, H., Wang, Y., Yan, Z., Zhang, J., & Wang, Y.
- Affiliations
- Xiaomi (China) (CN)
- Venue
- ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- Publisher
- IEEE
- Published
- 2023-06-04
- Pages
- 1-5
- ISSN
- 1520-6149 (ISSN-L)
- OpenAlex
- W4375869243
- Cited by
- 4
- References
- 3
- Citations by year
- 2026: 1 · 2024: 1 · 2023: 2
- FWCI
- 0.71
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE International Conference on Acoustics Speech and Signal Processing (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Physical Sciences › Computer Science › Signal Processing › Music and Audio Processing
- Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
- Keywords
- keyword spotting, audio tagging, mobile device deployment, transformer models, model compression, inference speed, human-machine interaction, intelligent assistants, AudioSet
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
