Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies
if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the
same subfield and year (this is the minimum needed to enter the top 1%, not the average
within it), or reaches the top citation threshold in at least one of its specific research
topics.
Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition
20112.1k citationsDong Yu, Alex Acero et al.IEEE Transactions on Audio Speech and Language Processingprofile →
Learning deep structured semantic models for web search using clickthrough data
20131.1k citationsXiaodong He, Li Deng et al.profile →
This map shows the geographic impact of Alex Acero's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Alex Acero with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Alex Acero more than expected).
This network shows the impact of papers produced by Alex Acero. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Alex Acero. The network helps show where Alex Acero may publish in the future.
Co-authorship network of co-authors of Alex Acero
This figure shows the co-authorship network connecting the top 25 collaborators of Alex Acero.
A scholar is included among the top collaborators of Alex Acero based on the total number of
citations received by their joint publications. Widths of edges
represent the number of papers authors have co-authored together.
Node borders
signify the number of papers an author published with Alex Acero. Alex Acero is excluded from
the visualization to improve readability, since they are connected to all nodes in the network.
All Works
20 of 20 papers shown
1.
He, Xiaodong, Amittai Axelrod, Li Deng, et al.. (2011). The MSR SYSTEM for IWSLT 2011 evaluation.. IWSLT. 57–61.3 indexed citations
Deng, Li, Michael L. Seltzer, Dong Yu, et al.. (2010). Binary coding of speech spectrograms using a deep auto-encoder. 1692–1695.243 indexed citations breakdown →
Tashev, Ivan, Jasha Droppo, & Alex Acero. (2006). Suppression Rule for Speech Recognition Friendly Noise Suppressors.2 indexed citations
9.
Wang, Ye‐Yi, John Lee, Milind Mahajan, & Alex Acero. (2005). Statistical Spoken Language Understanding: from Generative Model to Conditional Model. Neural Information Processing Systems.2 indexed citations
Wang, Ye‐Yi, Li Deng, & Alex Acero. (2005). Spoken language understanding. IEEE Signal Processing Magazine. 22(5). 16–31.75 indexed citations
12.
Chelba, Ciprian & Alex Acero. (2004). Adaptation of Maximum Entropy Capitalizer: Little Data Can Help a Lo.. Empirical Methods in Natural Language Processing. 285–292.78 indexed citations
Li, Deng, Jasha Droppo, & Alex Acero. (2002). Log-Domain Speech Feature Enhancement Using Sequential MAP Noise Estimation and a Phase-sensitive Model of the Acoustic Environment.8 indexed citations
16.
Frey, Brendan J., Trausti Kristjansson, Li Deng, & Alex Acero. (2001). ALGONQUIN - Learning Dynamic Noise Models From Noisy Speech for Robust Speech Recognition. Neural Information Processing Systems. 14. 1165–1171.14 indexed citations
Attias, Hagai, John Platt, Alex Acero, & Deng Li. (2000). Speech Denoising and Dereverberation Using Probabilistic Models. Neural Information Processing Systems. 13. 758–764.63 indexed citations
Acero, Alex. (1993). A Robust HMM-Based Endpoint Detector for Telecommunication Applications. Conference of the International Speech Communication Association.3 indexed citations
Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive
bibliographic database. While OpenAlex provides broad and valuable coverage of the global
research landscape, it—like all bibliographic datasets—has inherent limitations. These include
incomplete records, variations in author disambiguation, differences in journal indexing, and
delays in data updates. As a result, some metrics and network relationships displayed in
Rankless may not fully capture the entirety of a scholar's output or impact.