Pedro J. Moreno Mengibar

Most-cited papers

Supervised Learning of Semantic Classes for Image Annotation and Retrieval
G. Carneiro, Antoni B. Chan, Pedro J. Moreno Mengibar, N. Vasconcelos
2007IEEE Transactions on Pattern Analysis and Machine Intelligence1,005 citations Open access
Semantic Scholar
A Kullback-Leibler Divergence Based Kernel for SVM Classification in Multimedia Applications
Pedro J. Moreno Mengibar, Purdy Ho, N. Vasconcelos
2003Neural Information Processing Systems469 citations
Semantic Scholar
Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages
Yu Zhang, Wei Han, James Qin, Yongqiang Wang +23 more
2023arXiv.org414 citations Open access
Semantic Scholar
Multilingual Speech Recognition with a Single End-to-End Model
Shubham Toshniwal, T. Sainath, Ron J. Weiss, Bo Li +3 more
2017IEEE International Conference on Acoustics, Speech, and Signal Processing297 citations Open access
Semantic Scholar
Bridging the Gap: Query by Semantic Example
Nikhil Rasiwasia, Pedro J. Moreno Mengibar, N. Vasconcelos
2007IEEE transactions on multimedia292 citations Open access
Semantic Scholar
Automatic language identification using deep neural networks
I. López-Moreno, J. Gonzalez-Dominguez, O. Plchot, David Martínez +2 more
2014IEEE International Conference on Acoustics, Speech, and Signal Processing265 citations
Semantic Scholar
On the use of support vector machines for phonetic classification
P. Clarkson, Pedro J. Moreno Mengibar
19991999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258)215 citations
Semantic Scholar
Topic segmentation with an aspect hidden Markov model
D. Blei, Pedro J. Moreno Mengibar
2001Annual International ACM SIGIR Conference on Research and Development in Information Retrieval203 citations
Semantic Scholar
Automatic language identification using long short-term memory recurrent neural networks
J. Gonzalez-Dominguez, I. López-Moreno, Hasim Sak, J. González-Rodríguez +1 more
2014Interspeech164 citations
Semantic Scholar
From Audio to Semantics: Approaches to End-to-End Spoken Language Understanding
Parisa Haghani, Arun Narayanan, M. Bacchiani, Galen Chuang +5 more
2018Spoken Language Technology Workshop159 citations Open access
Semantic Scholar
Speech Recognition with Augmented Synthesized Speech
A. Rosenberg, Yu Zhang, B. Ramabhadran, Ye Jia +3 more
2019Automatic Speech Recognition & Understanding157 citations Open access
Semantic Scholar
A recursive algorithm for the forced alignment of very long audio segments
Pedro J. Moreno Mengibar, Christopher F. Joerg, J. Van Thong, Oren Glickman
1998ICSLP157 citations
Semantic Scholar
A Study of Musical Instrument Classification Using Gaussian Mixture Models and Support Vector Machines
Janet Marques, Pedro J. Moreno Mengibar
1999133 citations
Semantic Scholar
Semantic analysis of song lyrics
Beth Logan, A. Kositsky, Pedro J. Moreno Mengibar
2004IEEE International Conference on Multimedia and Expo132 citations
Semantic Scholar
Parrotron: An End-to-End Speech-to-Speech Conversion Model and its Applications to Hearing-Impaired Speech and Speech Separation
Fadi Biadsy, Ron J. Weiss, Pedro J. Moreno Mengibar, D. Kanvesky +1 more
2019Interspeech130 citations Open access
Semantic Scholar
MAESTRO: Matched Speech Text Representations through Modality Matching
Zhe-Huai Chen, Yu Zhang, A. Rosenberg, B. Ramabhadran +3 more
2022Interspeech125 citations Open access
Semantic Scholar
Bringing contextual information to google speech recognition
Petar S. Aleksic, M. Ghodsi, A. Michaely, Cyril Allauzen +4 more
2015Interspeech112 citations
Semantic Scholar
Using the Fisher kernel method for Web audio classification
Pedro J. Moreno Mengibar, R. Rifkin
20002000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100)90 citations
Semantic Scholar
Speechbot: an experimental speech-based search engine for multimedia content on the web
J. Van Thong, Pedro J. Moreno Mengibar, Beth Logan, B. Fidler +2 more
2002IEEE Trans. Multim.89 citations Open access
Semantic Scholar
Building transcribed speech corpora quickly and cheaply for many languages
Thad Hughes, Kaisuke Nakajima, Linne Ha, Atul Vasu +2 more
2010Interspeech87 citations
Semantic Scholar
Frame-by-frame language identification in short utterances using deep neural networks
J. Gonzalez-Dominguez, I. López-Moreno, Pedro J. Moreno Mengibar, J. González-Rodríguez
2015Neural Networks76 citations Open access
Semantic Scholar
An audio indexing system for election video material
C. Alberti, M. Bacchiani, Ari Bezman, Ciprian Chelba +7 more
2009IEEE International Conference on Acoustics, Speech, and Signal Processing75 citations
Semantic Scholar
On the use of deep feedforward neural networks for automatic language identification
I. López-Moreno, J. Gonzalez-Dominguez, David Martínez, O. Plchot +2 more
2016Computer Speech and Language73 citations Open access
Semantic Scholar
Data-driven environmental compensation for speech recognition: A unified approach
Pedro J. Moreno Mengibar, Bhiksha Raj, R. Stern
1998Speech Communication73 citations Open access
Semantic Scholar
Asynchronous stochastic optimization for sequence training of deep neural networks: towards big data
E. McDermott, G. Heigold, Pedro J. Moreno Mengibar, A. Senior +1 more
2014Interspeech69 citations
Semantic Scholar
A Real-Time End-to-End Multilingual Speech Recognition Architecture
J. Gonzalez-Dominguez, David Eustis, I. López-Moreno, A. Senior +2 more
2015IEEE Journal on Selected Topics in Signal Processing61 citations Open access
Semantic Scholar
COMPENSATION FOR ENVIRONMENTAL DEGRADATION IN AUTOMATIC SPEECH RECOGNITION
R. Stern, Bhiksha Raj, Pedro J. Moreno Mengibar
199961 citations
Semantic Scholar
A Family of Probabilistic Kernels Based on Information Divergence
Antoni B. Chan, N. Vasconcelos, Pedro J. Moreno Mengibar
200459 citations
Semantic Scholar
Approaches to reduce the effects of OOV queries on indexed spoken audio
Beth Logan, J. Van Thong, Pedro J. Moreno Mengibar
2005IEEE transactions on multimedia58 citations Open access
Semantic Scholar
The Kullback-Leibler Kernel as a Framework for Discriminant and Localized Representations for Visual Recognition
N. Vasconcelos, Purdy Ho, Pedro J. Moreno Mengibar
2004European Conference on Computer Vision57 citations Open access
Semantic Scholar
An experimental study of an audio indexing system for the web
Beth Logan, Pedro J. Moreno Mengibar, J. Van Thong, E. Whittaker
2000Interspeech57 citations
Semantic Scholar
Improving Speech Recognition Using Consistent Predictions on Synthesized Speech
Gary Wang, A. Rosenberg, Zhe-Huai Chen, Yu Zhang +3 more
2020IEEE International Conference on Acoustics, Speech, and Signal Processing55 citations
Semantic Scholar
A new SVM approach to speaker identification and verification using probabilistic distance kernels
Pedro J. Moreno Mengibar, Purdy Ho
2003Interspeech53 citations
Semantic Scholar
Factorial HMMs for acoustic modeling
Beth Logan, Pedro J. Moreno Mengibar
1998Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181)53 citations
Semantic Scholar
A boosting approach for confidence scoring
Pedro J. Moreno Mengibar, Beth Logan, Bhiksha Raj
2001Interspeech52 citations
Semantic Scholar
Word and sub-word indexing approaches for reducing the effects of OOV queries on spoken audio
Beth Logan, Pedro J. Moreno Mengibar, Om Deshmukh
200251 citations Open access
Semantic Scholar
Improved recognition of contact names in voice commands
Petar S. Aleksic, Cyril Allauzen, David K. Elson, Aleksandar Kracun +2 more
2015IEEE International Conference on Acoustics, Speech, and Signal Processing50 citations
Semantic Scholar
A factor automaton approach for the forced alignment of long speech recordings
Pedro J. Moreno Mengibar, C. Alberti
2009IEEE International Conference on Acoustics, Speech, and Signal Processing50 citations
Semantic Scholar
Google's cross-dialect Arabic voice search
Fadi Biadsy, Pedro J. Moreno Mengibar, Martin Jansche
2012IEEE International Conference on Acoustics, Speech, and Signal Processing47 citations
Semantic Scholar
Transliteration Based Approaches to Improve Code-Switched Speech Recognition Performance
Jesse Emond, B. Ramabhadran, Brian Roark, Pedro J. Moreno Mengibar +1 more
2018Spoken Language Technology Workshop41 citations
Semantic Scholar
Injecting Text in Self-Supervised Speech Pretraining
Zhe-Huai Chen, Yu Zhang, A. Rosenberg, B. Ramabhadran +2 more
2021Automatic Speech Recognition & Understanding39 citations Open access
Semantic Scholar
Improving Speech Recognition Using GAN-Based Speech Synthesis and Contrastive Unspoken Text Selection
Zhe-Huai Chen, A. Rosenberg, Yu Zhang, Gary Wang +2 more
2020Interspeech39 citations
Semantic Scholar
Extending Parrotron: An End-to-End, Speech Conversion and Speech Recognition Model for Atypical Speech
Rohan Doshi, Youzheng Chen, Liyang Jiang, Xia Zhang +5 more
2021IEEE International Conference on Acoustics, Speech, and Signal Processing37 citations
Semantic Scholar
Multi-Dialectical Languages Effect on Speech Recognition: Too Much Choice Can Hurt
M. Elfeky, Pedro J. Moreno Mengibar, V. Soto
2016International Conference on Natural Language and Speech Processing37 citations Open access
Semantic Scholar
Multilingual Speech Recognition with Self-Attention Structured Parameterization
Yun Zhu, Parisa Haghani, Anshuman Tripathi, B. Ramabhadran +8 more
2020Interspeech36 citations
Semantic Scholar
Leveraging Language ID in Multilingual End-to-End Speech Recognition
Austin Waters, Neeraj Gaur, Parisa Haghani, Pedro J. Moreno Mengibar +1 more
2019Automatic Speech Recognition & Understanding36 citations
Semantic Scholar
Query by Semantic Example
Nikhil Rasiwasia, N. Vasconcelos, Pedro J. Moreno Mengibar
2006ACM International Conference on Image and Video Retrieval36 citations
Semantic Scholar
Audiovisual celebrity recognition in unconstrained web videos
M. E. Sargin, H. Aradhye, Pedro J. Moreno Mengibar, Ming Zhao
2009IEEE International Conference on Acoustics, Speech, and Signal Processing34 citations
Semantic Scholar
SpeechBot: a Speech Recognition based Audio Indexing System for the Web
D. Goddeau, Anna Litvinova, Beth Logan, Pedro J. Moreno Mengibar +2 more
2000RIAO Conference34 citations
Semantic Scholar
Towards acoustic model unification across dialects
M. Elfeky, M. Bastani, Xavier Velez, Pedro J. Moreno Mengibar +1 more
2016Spoken Language Technology Workshop33 citations
Semantic Scholar