Karen Livescu

发表

A factored conditional random field model for articulatory feature forced transcription

Eric Fosler-Lussier, Rohit Prabhavalkar, Karen Livescu, 2011, 2011 IEEE Workshop on Automatic Speech Recognition & Understanding.

From Paraphrase Database to Compositional Paraphrase Model and Back

Kevin Gimpel, Karen Livescu, John Wieting, 2015, Transactions of the Association for Computational Linguistics.

Proceedings of the Student Research Workshop at HLT-NAACL 2004, Boston, Massachusetts, USA, May 2-7, 2004

Ani Nenkova, Karen Livescu, Nicola Stokes, 2004, HLT-NAACL.

Deep Canonical Correlation Analysis

Jeff A. Bilmes, Raman Arora, Karen Livescu, 2013, ICML.

Multi-view learning with supervision for transformed bottleneck features

Raman Arora, Karen Livescu, R. Arora, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Fixed-dimensional acoustic embeddings of variable-length segments in low-resource settings

Aren Jansen, Karen Livescu, Keith Levin, 2013, 2013 IEEE Workshop on Automatic Speech Recognition and Understanding.

Reconstruction of articulatory measurements with smoothed low-rank matrix completion

Raman Arora, Karen Livescu, Weiran Wang, 2014, 2014 IEEE Spoken Language Technology Workshop (SLT).

Feature-based Pronunciation Modeling for Speech Recognition

James R. Glass, Karen Livescu, 2004, HLT-NAACL.

A Study of All-Convolutional Encoders for Connectionist Temporal Classification

Liang Lu, Kevin Gimpel, Karen Livescu, 2017, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Discriminative articulatory models for spoken term detection in low-resource conversational settings

Rohit Prabhavalkar, Karen Livescu, Joseph Keshet, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Feature-based pronunciation modeling with trainable asynchrony probabilities

James R. Glass, Karen Livescu, 2004, INTERSPEECH.

Acoustic Feature Learning Using Cross-Domain Articulatory Measurements

Karen Livescu, Weiran Wang, Qingming Tang, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

A Comparison of Techniques for Language Model Integration in Encoder-Decoder Speech Recognition

Tara N. Sainath, Yonghui Wu, Karen Livescu, 2018, 2018 IEEE Spoken Language Technology Workshop (SLT).

Feature-based pronunciation modeling for automatic speech recognition

Karen Livescu, Karen Livescu, 2005 .

On the Role of Supervision in Unsupervised Constituency Parsing

Kevin Gimpel, Karen Livescu, Haoyue Shi, 2020, EMNLP.

Analysis and modeling of non-native speech for automatic speech recognition

Karen Livescu, 1999 .

End-to-End Neural Segmental Models for Speech Recognition

Hao Tang, Chris Dyer, Steve Renals, 2017, IEEE Journal of Selected Topics in Signal Processing.

American sign language fingerspelling recognition with phonological feature-based tandem models

Gregory Shakhnarovich, Karen Livescu, Taehwan Kim, 2012, 2012 IEEE Spoken Language Technology Workshop (SLT).

Towards Universal Paraphrastic Sentence Embeddings pdf

Kevin Gimpel, Karen Livescu, John Wieting, 2015, ICLR.

Modeling pronunciation variation with context-dependent articulatory feature decision trees

Samuel R. Bowman, Karen Livescu, 2010, INTERSPEECH.

Domain Adaptation with Unlabeled Data for Dialog Act Tagging

Mari Ostendorf, Karen Livescu, Anna Margolis, 2010 .

Unsupervised Pre-Training of Bidirectional Speech Encoders via Masked Reconstruction

Karen Livescu, Weiran Wang, Qingming Tang, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

On Deep Multi-View Representation Learning pdf

Jeff A. Bilmes, Raman Arora, Karen Livescu, 2015, ICML.

Phonological models in automatic speech recognition: invited talk

Karen Livescu, 2008, ACL 2008.

Low-Resource Speech-to-Text Translation

Adam Lopez, Karen Livescu, Sharon Goldwater, 2018, INTERSPEECH.

Revisiting Word Neighborhoods for Speech Recognition

Karen Livescu, Preethi Jyothi, Karen Livescu, 2014, SIGMORPHON/SIGFSM.

Hierarchical Multitask Learning for CTC-based Speech Recognition pdf

Karen Livescu, Shubham Toshniwal, Kalpesh Krishna, 2018, ArXiv.

Articulatory feature-based pronunciation modeling

Eric Fosler-Lussier, Karen Livescu, Preethi Jyothi, 2016, Comput. Speech Lang..

On Deep Multi-View Representation Learning

Jeff A. Bilmes, Raman Arora, Karen Livescu, 2015, ICML.

Segment-based recognition on the phonebook task: initial results and observations on duration modeling

James R. Glass, Karen Livescu, Karen Livescu, 2001, INTERSPEECH.

Deep convolutional acoustic word embeddings using word-pair side information

Karen Livescu, Weiran Wang, Herman Kamper, 2015, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Speech Production in Speech Technologies: Introduction to the CSL Special Issue

Jeff A. Bilmes, Frank Rudzicz, Mark Hasegawa-Johnson, 2016, Comput. Speech Lang..

Multi-view Recurrent Neural Acoustic Word Embeddings pdf

Karen Livescu, Weiran Wang, Wanjia He, 2016, ICLR.

Multitask Learning with Low-Level Auxiliary Tasks for Encoder-Decoder Based Speech Recognition pdf

Liang Lu, Karen Livescu, Hao Tang, 2017, INTERSPEECH.

Production domain modeling of pronunciation for visual speech recognition

Trevor Darrell, James R. Glass, Kate Saenko, 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

Lexicon-free fingerspelling recognition from video: Data, models, and signer adaptation pdf

Gregory Shakhnarovich, Diane Brentari, Karen Livescu, 2017, Comput. Speech Lang..

Audio-visual anticipatory coarticulation modeling by human and machine

Aggelos K. Katsaggelos, Karen Livescu, Louis H. Terry, 2010, INTERSPEECH.

Articulatory Feature Classification Using Nearest Neighbors

Rohit Prabhavalkar, Karen Livescu, Arild Brandrud Næss, 2011, INTERSPEECH.

An Articulatory Feature-Based Tandem Approach and Factored Observation Modeling

Simon King, Karen Livescu, Chris D. Bartels, 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

Multi-view CCA-based acoustic features for phonetic recognition across speakers and domains

Raman Arora, Karen Livescu, R. Arora, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Jointly learning to align and convert graphemes to phonemes with neural attention models

Karen Livescu, Shubham Toshniwal, Karen Livescu, 2016, 2016 IEEE Spoken Language Technology Workshop (SLT).

Multi-view clustering via canonical correlation analysis

Sham M. Kakade, Kamalika Chaudhuri, Karthik Sridharan, 2009, ICML '09.

Acoustic Feature Learning via Deep Variational Canonical Correlation Analysis pdf

Karen Livescu, Weiran Wang, Qingming Tang, 2017, INTERSPEECH.

Semantic Speech Retrieval With a Visually Grounded Model of Untranscribed Speech

Gregory Shakhnarovich, Karen Livescu, Herman Kamper, 2017, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Deep Multilingual Correlation for Improved Word Embeddings

Kevin Gimpel, Karen Livescu, Mohit Bansal, 2015, HLT-NAACL.

Discriminative segmental cascades for feature-rich phone recognition

Kevin Gimpel, Karen Livescu, Hao Tang, 2015, 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU).

Subword Modeling for Automatic Speech Recognition: Past, Present, and Emerging Approaches

Florian Metze, Karen Livescu, Eric Fosler-Lussier, 2012, IEEE Signal Processing Magazine.

Nonparametric Canonical Correlation Analysis pdf

Karen Livescu, Tomer Michaeli, Weiran Wang, 2015, ICML.

Acoustic span embeddings for multilingual query-by-example search pdf

Karen Livescu, Yushi Hu, Shane Settle, 2020, ArXiv.

An embedded segmental K-means model for unsupervised segmentation and clustering of speech

Karen Livescu, Sharon Goldwater, Herman Kamper, 2017, 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

Fingerspelling Recognition in the Wild With Iterative Visual Attention

Karen Livescu, Greg Shakhnarovich, Bowen Shi, 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

Large-Scale Approximate Kernel Canonical Correlation Analysis pdf

Karen Livescu, Weiran Wang, Weiran Wang, 2015, ICLR.

End-to-end training approaches for discriminative segmental models

Kevin Gimpel, Karen Livescu, Hao Tang, 2016, 2016 IEEE Spoken Language Technology Workshop (SLT).

A Correspondence Variational Autoencoder for Unsupervised Acoustic Word Embeddings pdf

Karen Livescu, Herman Kamper, Puyuan Peng, 2020, ArXiv.

Variational Sequential Labelers for Semi-Supervised Learning pdf

Kevin Gimpel, Karen Livescu, Mingda Chen, 2019, EMNLP.

Learning to Ignore: Long Document Coreference with Bounded Memory Neural Networks

Allyson Ettinger, Kevin Gimpel, Sam Wiseman, 2020, EMNLP.

American Sign Language Fingerspelling Recognition in the Wild

Gregory Shakhnarovich, Diane Brentari, Karen Livescu, 2018, 2018 IEEE Spoken Language Technology Workshop (SLT).

Discriminative Pronunciation Modeling: A Large-Margin, Feature-Rich Approach

Karen Livescu, Joseph Keshet, Hao Tang, 2012, ACL.

Substructure Substitution: Structured Data Augmentation for NLP pdf

Kevin Gimpel, Haoyue Shi, Karen Livescu, 2021, FINDINGS.

Signer-independent fingerspelling recognition with deep neural network adaptation

Karen Livescu, Hao Tang, Weiran Wang, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Query-by-Example Search with Discriminative Neural Acoustic Word Embeddings

Karen Livescu, Herman Kamper, Keith Levin, 2017, INTERSPEECH.

Triphone State-Tying via Deep Canonical Correlation Analysis

Karen Livescu, Hao Tang, Weiran Wang, 2016, INTERSPEECH.

Tailoring Continuous Word Representations for Dependency Parsing

Kevin Gimpel, Karen Livescu, Mohit Bansal, 2014, ACL.

Landmark-based speech recognition: report of the 2004 Johns Hopkins summer workshop

Mark Hasegawa-Johnson, Sarah Borys, Karen Livescu, 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

Monolingual and crosslingual comparison of tandem features derived from articulatory and phone MLPS

Simon King, Karen Livescu, Chris D. Bartels, 2007, 2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU).

A Cross-Task Analysis of Text Span Representations

Kevin Gimpel, Karen Livescu, Shubham Toshniwal, 2020, REPL4NLP.

Semantic Query-by-example Speech Search Using Visual Grounding

Karen Livescu, Herman Kamper, Aristotelis Anastassiou, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Pre-Trained Text Embeddings for Enhanced Text-to-Speech Synthesis

Tomoki Toda, Shinji Watanabe, Kazuya Takeda, 2019, INTERSPEECH.

AN ASYNCHRONOUS DBN FOR AUDIO-VISUAL SPEECH RECOGNITION

Kate Saenko, Karen Livescu, Kate Saenko, 2006, 2006 IEEE Spoken Language Technology Workshop.

Pre-training on high-resource speech recognition improves low-resource speech-to-text translation pdf

Adam Lopez, Karen Livescu, Sharon Goldwater, 2018, NAACL.

Efficient Segmental Cascades for Speech Recognition pdf

Kevin Gimpel, Karen Livescu, Hao Tang, 2016, INTERSPEECH.

Parsing Speech: a Neural Approach to Integrating Lexical and Acoustic-Prosodic Information

Mari Ostendorf, Trang Tran, Kevin Gimpel, 2017, NAACL.

Visual speech recognition with loosely synchronized feature streams

Trevor Darrell, James R. Glass, Kate Saenko, 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

Joint Modeling of Text and Acoustic-Prosodic Cues for Neural Parsing pdf

Mari Ostendorf, Trang Tran, Kevin Gimpel, 2017, ArXiv.

PeTra: A Sparsely Supervised Memory Model for People Tracking pdf

Allyson Ettinger, Kevin Gimpel, Karen Livescu, 2020, ACL.

Discriminative training of WFST factors with application to pronunciation modeling

Eric Fosler-Lussier, Karen Livescu, Preethi Jyothi, 2013, INTERSPEECH.

Multitask training with unlabeled data for end-to-end sign language fingerspelling recognition

Karen Livescu, Bowen Shi, 2017, 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

Charagram: Embedding Words and Sentences via Character n-grams pdf

Kevin Gimpel, Karen Livescu, John Wieting, 2016, EMNLP.

Kernel CCA for multi-view learning of acoustic features using articulatory measurements

Raman Arora, Karen Livescu, R. Arora, 2012, MLSLP.

On the Contributions of Visual and Textual Supervision in Low-resource Semantic Speech Retrieval

Karen Livescu, Ankita Pasad, Bowen Shi, 2019, INTERSPEECH.

Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing

David Yarowsky, Timothy Baldwin, Steven Bethard, 2013, EMNLP 2013.

Lexical access experiments with context-dependent articulatory feature-based models

Eric Fosler-Lussier, Karen Livescu, Preethi Jyothi, 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Lexical modeling of non-native speech for automatic speech recognition

James R. Glass, Karen Livescu, Karen Livescu, 2000, 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100).

Acoustically Grounded Word Embeddings for Improved Acoustics-to-word Speech Recognition

Michael Picheny, Karen Livescu, Kartik Audhkhasi, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Deep Variational Canonical Correlation Analysis pdf

Honglak Lee, Karen Livescu, Weiran Wang, 2016, ArXiv.

Speech production knowledge in automatic speech recognition.

Simon King, Karen Livescu, Erik McDermott, 2007, The Journal of the Acoustical Society of America.

Unsupervised learning of acoustic features via deep canonical correlation analysis

Jeff A. Bilmes, Raman Arora, Karen Livescu, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Visually Grounded Neural Syntax Acquisition pdf

Kevin Gimpel, Karen Livescu, Jiayuan Mao, 2019, ACL.

Fingerspelling Recognition with Semi-Markov Conditional Random Fields

Gregory Shakhnarovich, Karen Livescu, Taehwan Kim, 2013, 2013 IEEE International Conference on Computer Vision.

Hidden feature models for speech recognition using dynamic Bayesian networks

James R. Glass, Jeff A. Bilmes, Karen Livescu, 2003, INTERSPEECH.

Discriminatively learning factorized finite state pronunciation models from dynamic Bayesian networks

Eric Fosler-Lussier, Karen Livescu, Preethi Jyothi, 2012, INTERSPEECH.

Nearest Neighbors with Learned Distances for Phonetic Frame Classification

Karen Livescu, John Labiak, 2011, INTERSPEECH.

Multilingual Jointly Trained Acoustic and Written Word Embeddings pdf

Karen Livescu, Yushi Hu, Shane Settle, 2020, INTERSPEECH.

Mapping Unseen Words to Task-Trained Embedding Spaces

Kevin Gimpel, Karen Livescu, Pranava Swaroop Madhyastha, 2015, Rep4NLP@ACL.

Discriminative spoken term detection with limited data

Eric Fosler-Lussier, Rohit Prabhavalkar, Karen Livescu, 2012, MLSLP.

Discriminative acoustic word embeddings: Tecurrent neural network-based approaches

Karen Livescu, Shane Settle, Karen Livescu, 2016, 2016 IEEE Spoken Language Technology Workshop (SLT).

On the phonetic information in ultrasonic microphone signals

James R. Glass, Bo Zhu, Karen Livescu, 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

Invited talk: Phonological Models in Automatic Speech Recognition

Karen Livescu, 2008, SIGMORPHON.

Visually Grounded Learning of Keyword Prediction from Untranscribed Speech

Gregory Shakhnarovich, Karen Livescu, Herman Kamper, 2017, INTERSPEECH.

Articulatory feature classifiers trained on 2000 hours of telephone speech

Simon King, Karen Livescu, Joe Frankel, 2007, INTERSPEECH.

Structurally discriminative graphical models for automatic speech recognition - results from the 2001 Johns Hopkins Summer Workshop

Geoffrey Zweig, Karim Filali, Jeff A. Bilmes, 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Multistream Articulatory Feature-Based Models for Visual Speech Recognition

Trevor Darrell, James R. Glass, James Glass, 2009, IEEE Trans. Pattern Anal. Mach. Intell..

Manual Transcription of Conversational Speech at the Articulatory Feature Level

Simon King, Karen Livescu, Joe Frankel, 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

Learning to Embed Words in Context for Syntactic Tasks

Lifu Tu, Kevin Gimpel, Karen Livescu, 2017, Rep4NLP@ACL.

Multi-view learning of acoustic features for speaker recognition

Karen Livescu, Mark Stoehr, Karen Livescu, 2009, 2009 IEEE Workshop on Automatic Speech Recognition & Understanding.

AUDIOVISUAL SPEECH RECOGNITION WITH ARTICULATOR POSITIONS AS HIDDEN VARIABLES

Kate Saenko, Mark Hasegawa-Johnson, Karen Livescu, 2007 .

Discrete Latent Variable Representations for Low-Resource Text Classification

Karl Stratos, Sam Wiseman, Karen Livescu, 2020, ACL.

A comparison of training approaches for discriminative segmental models

Kevin Gimpel, Karen Livescu, Hao Tang, 2014, INTERSPEECH.

Stochastic optimization for PCA and PLS

Nathan Srebro, Raman Arora, Andrew Cotter, 2012, 2012 50th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

Sub-word Modeling for Automatic Speech Recognition

Florian Metze, Karen Livescu, Eric Fosler-Lussier, 2012 .

Multiview acoustic feature learning using articulatory measurements

Mark Hasegawa-Johnson, Karen Livescu, Raman Arora, 2020 .

Whole-Word Segmental Speech Recognition with Acoustic Word Embeddings pdf

Karen Livescu, Bowen Shi, Shane Settle, 2020, ArXiv.

Variational recurrent models for representation learning

Karen Livescu, Weiran Wang, Mingda Chen, 2018 .

Articulatory Feature-Based Methods for Acoustic and Audio-Visual Speech Recognition: Summary from the 2006 JHU Summer workshop

Simon King, Kate Saenko, Mark Hasegawa-Johnson, 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

Stochastic optimization for deep CCA via nonlinear orthogonal iterations

Nathan Srebro, Raman Arora, Karen Livescu, 2015, 2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton).

Fingerspelling Detection in American Sign Language

Diane Brentari, Karen Livescu, Greg Shakhnarovich, 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

On the Use of External Data for Spoken Named Entity Recognition pdf

Karen Livescu, Ankita Pasad, Suwon Shon, 2021, ArXiv.

Substructure Distribution Projection for Zero-Shot Cross-Lingual Dependency Parsing pdf

Kevin Gimpel, Karen Livescu, Haoyue Shi, 2021, ACL.

Learning Chess Blindfolded: Evaluating Language Models on State Tracking pdf

Kevin Gimpel, Sam Wiseman, Karen Livescu, 2021, ArXiv.

On Generalization in Coreference Resolution pdf

Kevin Gimpel, Sam Wiseman, Karen Livescu, 2021, CRAC.

Layer-wise Analysis of a Self-supervised Speech Representation Model pdf

Karen Livescu, Ankita Pasad, Ju-Chieh Chou, 2021, ArXiv.

SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural Speech pdf

Yoav Artzi, Karen Livescu, Ankita Pasad, 2021, ArXiv.

Differential Representation of Articulatory Gestures and Phonemes in Precentral and Inferior Frontal Gyri

Karen Livescu, Marc W. Slutzky, Emily M. Mugler, 2018, The Journal of Neuroscience.

Attend and Pronounce : An Attention-Based Approach for Grapheme-To-Phoneme Conversion

Karen Livescu, Shubham Toshniwal, 2016 .

Differential Representation of Articulatory Gestures and Phonemes in Motor, Premotor, and Inferior Frontal Cortices

Karen Livescu, Marc W. Slutzky, Emily M. Mugler, 2017, bioRxiv.