Low-rank plus diagonal adaptation for deep neural networks
The DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Abstract
In this paper, we propose a scalable adaptation technique that adapts the deep neural network (DNN) model through the low-rank plus diagonal (LRPD) decomposition. It is desired that an adaptation method can properly accommodate the available development data with a variable amount of adaptation parameters. Thus, the resulting models neither over-fit nor under-fit as the development data vary in size for different speakers. The technique developed in this paper is inspired by observing that adaptation matrices are very close to an identity matrix or diagonally dominant. The LRPD restructures the adaptation matrix as a superposition of a diagonal matrix and a low-rank matrix. By varying the low-rank values, the LRPD contains the full and the diagonal adaptation matrix as its special cases. Experimental results demonstrated that the LRPD adaptation of the full-size DNN obtains improved accuracy over the standard linear adaptation. The LRPD bottleneck adaptation can reduce the speaker-specific footprint by 82% over an already very compact SVD bottleneck adaptation, at an expense of 1% relative WER increase.
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.
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
Learning representations by back-propagating errors
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986) · Nature · doi:10.1038/323533a0 · Cited by 31,892
Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition
Dahl, G. E., Yu, D., Deng, L., & Acero, A. (2012) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/tasl.2011.2134090 · Cited by 3,011 · cited 4×
“For CD-DNN-HMMs [1], the output layer is normalized by the softmax function to produce the posterior probability of senone id s, p(s|x).”
BackgroundMethodInfluentialRecent advances in deep learning for speech research at Microsoft
Deng, L., Li, J., Huang, J.-T., Yao, K., Yu, D., Seide, F., Seltzer, M., Zweig, G., He, X., Williams, J., et al. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6639345 · Cited by 801 · cited 1×
“The discovery of the strong modeling capabilities of deep neural networks (DNNs) [1], [2], [3], [4] and the availability of high-speed hardware has made it feasible to train large networks with tens of millions of parameters.”
BackgroundSelf-citationSwietojanski, P., & Renals, S. (2014) · 2014 IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt.2014.7078569 · Cited by 218
Li, B., & Sim, K. C. (2010) · Interspeech 2010 · doi:10.21437/interspeech.2010-214 · Cited by 155
Cited by
LoRA: Low-Rank Adaptation of Large Language Models
Hu, E. J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., & Chen, W. (2021) · arXiv · doi:10.48550/arxiv.2106.09685 · Cited by 13,453
“Some prior works even explicitly impose the low-rank constraint when training the original neural network, such as [17, 30, 35, 38, 39], however, to the best of our knowledge, none of these works considers low-rank update for adaptation to downstream tasks.”
BackgroundGeng, M., Xie, X., Ye, Z., Wang, T., Li, G., Hu, S., Liu, X., & Meng, H. (2022) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2022.3195113 · Cited by 48
On-device personalization of automatic speech recognition models for disordered speech
Tomanek, K., Beaufays, F., Cattiau, J., Chandorkar, A., & Sim, K. C. (2021) · arXiv · doi:10.48550/arxiv.2106.10259 · Cited by 14
“AM adaptation techniques [21, 22, 23, 24, 25, 26, 27, 28, 29] attempt to reduce mismatch in terms of users’ voice characteristics, such as accent, pitch and speaking rate.”
BackgroundHMC-T RAN: A Tensor-core Inspired Hierarchical Model Compression for Transformer-based DNNs on GPU
Huang, S., Chen, S., Peng, H., Manu, D., Kong, Z., Yuan, G., Yang, L., Wang, S., Liu, H., & Ding, C. (2021) · Proceedings of the 2021 Great Lakes Symposium on VLSI · doi:10.1145/3453688.3461740 · Cited by 4
Metadata
- Authors
- Zhao, Y., Li, J., & Gong, Y.
- Venue
- 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- Publisher
- IEEE
- Published
- 2016-03
- Pages
- 5005-5009
- ISSN
- 1520-6149 (ISSN-L)
- OpenAlex
- W2394882406
- Cited by
- 61
- References
- 5
- FWCI
- 4.90
- Type
- conference paper
- Language
- en
- Open access
- closed
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: Low-rank plus diagonal adaptation for deep neural networks. https://app.cochat.ai/papers/10.1109/icassp.2016.7472630
- The paper
- Zhao, Y., Li, J., & Gong, Y. (2016). Low-rank plus diagonal adaptation for deep neural networks. 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https://doi.org/10.1109/icassp.2016.7472630
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.