H-Index & Metrics Top Publications

H-Index & Metrics

Discipline name H-index Citations Publications World Ranking National Ranking
Computer Science H-index 59 Citations 9,971 196 World Ranking 1634 National Ranking 913

Research.com Recognitions

Awards & Achievements

2004 - IEEE Fellow For contributions to noise robust speech recognition and speech technology education.

Overview

What is he best known for?

The fields of study he is best known for:

  • Artificial intelligence
  • Speech recognition
  • Statistics

Alejandro Acero focuses on Speech recognition, Artificial intelligence, Natural language processing, Speech processing and Word error rate. The various areas that Alejandro Acero examines in his Speech recognition study include Context, Normalization and Noise. His Artificial intelligence study frequently draws connections between adjacent fields such as Pattern recognition.

His studies deal with areas such as Web search query and Classifier as well as Natural language processing. His research integrates issues of Minimum mean square error and Speech enhancement in his study of Speech processing. His Word error rate study combines topics in areas such as Word, Pruning, Index and Audio mining.

His most cited work include:

  • Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition (2360 citations)
  • Method and system of runtime acoustic unit selection for speech synthesis (266 citations)
  • Method and apparatus for multi-sensory speech enhancement (214 citations)

What are the main themes of his work throughout his whole career to date?

His main research concerns Speech recognition, Artificial intelligence, Pattern recognition, Natural language processing and Signal. Alejandro Acero works mostly in the field of Speech recognition, limiting it down to concerns involving Noise and, occasionally, Reduction. His Discriminative model, Hidden Markov model, Natural language, Word and Feature vector investigations are all subjects of Artificial intelligence research.

His research investigates the connection between Pattern recognition and topics such as Distortion that intersect with problems in Channel. The Natural language processing study combines topics in areas such as Grammar and Adaptive grammar. His biological study spans a wide range of topics, including Acoustics, Noise reduction and Value.

He most often published in these fields:

  • Speech recognition (56.63%)
  • Artificial intelligence (37.86%)
  • Pattern recognition (18.45%)

What were the highlights of his more recent work (between 2007-2016)?

  • Speech recognition (56.63%)
  • Artificial intelligence (37.86%)
  • Pattern recognition (18.45%)

In recent papers he was focusing on the following fields of study:

His primary areas of study are Speech recognition, Artificial intelligence, Pattern recognition, Natural language processing and Noise. Speech recognition and Speech enhancement are frequently intertwined in his study. His Artificial intelligence research includes elements of Probability distribution and Adaptation.

His study in Pattern recognition focuses on Hidden Markov model in particular. His studies in Natural language processing integrate themes in fields like Query expansion, Information retrieval and Web query classification. He interconnects Minimum mean square error, Acoustic model, Decoding methods and Probabilistic logic in the investigation of issues within Noise.

Between 2007 and 2016, his most popular works were:

  • Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition (2360 citations)
  • Spatial Audio for Audio Conferencing (105 citations)
  • Multichannel acoustic echo reduction (104 citations)

In his most recent research, the most cited papers focused on:

  • Artificial intelligence
  • Programming language
  • Statistics

Alejandro Acero mainly investigates Speech recognition, Artificial intelligence, Noise, Hidden Markov model and Word error rate. His Speech recognition research is multidisciplinary, incorporating perspectives in Context model and Phrase. His Artificial intelligence study incorporates themes from Pronunciation, Natural language processing, Query language and Pattern recognition.

His work in Pattern recognition covers topics such as Artificial neural network which are related to areas like Sequence, Feature vector and Word. His Hidden Markov model research incorporates themes from Restricted Boltzmann machine, Parallelizable manifold, Mathematical optimization and Rendering. His Word error rate research is multidisciplinary, incorporating elements of Context, Statistical classification, Mixture model, Discriminative model and Piecewise.

This overview was generated by a machine learning system which analysed the scientist’s body of work. If you have any feedback, you can contact us here.

Top Publications

Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition

G. E. Dahl;Dong Yu;Li Deng;A. Acero.
IEEE Transactions on Audio, Speech, and Language Processing (2012)

2923 Citations

Text-to-speech using clustered context-dependent phoneme-based units

Alejandro Acero;Hsiao-Wuen Hon;Xuedong D. Huang.
Journal of the Acoustical Society of America (1997)

354 Citations

Method and system of runtime acoustic unit selection for speech synthesis

Huang Xuedong D;Plumpe Michael D;Acero Alejandro;Adcock James L.
(1997)

342 Citations

Multiple approaches to robust speech recognition

Richard M. Stern;Fu-Hua Liu;Yoshiaki Ohshima;Thomas M. Sullivan.
human language technology (1992)

263 Citations

Method and apparatus for multi-sensory speech enhancement

Alejandro Acero;James G. Droppo;Li Deng;Michael J. Sinclair.
(2004)

254 Citations

Combined speech and alternate input modality to a mobile device

Milind V. Mahajan;Alejandro Acero;Bo-June Hsu.
Journal of the Acoustical Society of America (2006)

250 Citations

Efficient cepstral normalization for robust speech recognition

Fu-Hua Liu;Richard M. Stern;Xuedong Huang;Alejandro Acero.
human language technology (1993)

222 Citations

Dynamic compensation of HMM variances using the feature enhancement uncertainty computed from a parametric model of speech distortion

Li Deng;J. Droppo;A. Acero.
IEEE Transactions on Speech and Audio Processing (2005)

216 Citations

Robust speech recognition by normalization of the acoustic space

A. Acero;R.M. Stern.
international conference on acoustics, speech, and signal processing (1991)

212 Citations

Method and apparatus for removing noise from feature vectors

Brendan J. Frey;Alejandro Acero;Li Deng.
Journal of the Acoustical Society of America (2001)

207 Citations

Profile was last updated on December 6th, 2021.
Research.com Ranking is based on data retrieved from the Microsoft Academic Graph (MAG).
The ranking h-index is inferred from publications deemed to belong to the considered discipline.

If you think any of the details on this page are incorrect, let us know.

Contact us

Top Scientists Citing Alejandro Acero

Li Deng

Li Deng

Citadel

Publications: 194

Dong Yu

Dong Yu

Tencent (China)

Publications: 154

Alex Acero

Alex Acero

Apple (United States)

Publications: 79

Jinyu Li

Jinyu Li

Microsoft (United States)

Publications: 69

Yifan Gong

Yifan Gong

Microsoft (United States)

Publications: 68

Mark J. F. Gales

Mark J. F. Gales

University of Cambridge

Publications: 47

Michael L. Seltzer

Michael L. Seltzer

Facebook (United States)

Publications: 43

Xiaodong He

Xiaodong He

Jingdong (China)

Publications: 42

Chin-Hui Lee

Chin-Hui Lee

Georgia Institute of Technology

Publications: 41

Thomas R. Gruber

Thomas R. Gruber

Apple (United States)

Publications: 33

Steve Renals

Steve Renals

University of Edinburgh

Publications: 33

Haizhou Li

Haizhou Li

Chinese University of Hong Kong, Shenzhen

Publications: 31

Jasha Droppo

Jasha Droppo

Amazon (United States)

Publications: 30

Martin T. King

Martin T. King

Google (United States)

Publications: 29

Jerome R. Bellegarda

Jerome R. Bellegarda

Apple (United States)

Publications: 27

Something went wrong. Please try again later.