Paul Vozila - researchr alias

researchr

You are not signed in
Sign in
Sign up

Viewing Publication 1 - 18 from 18

2025

A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks AlignmentJean-Philippe Corbeil, Amin Dada, Jean-Michel Attendu, Asma Ben Abacha, Alessandro Sordoni, Lucas Caccia, François Beaulieu, Thomas Lin, Jens Kleesiek, Paul Vozila. acl 2025: 19352-19374 [doi]

2023

Large Scale Sequence-to-Sequence Models for Clinical Note Generation from Patient-Doctor ConversationsGagandeep Singh, Yue Pan, Jesús Andrés-Ferrer, Miguel A. del Agua, Frank Diehl, Joel Pinto, Paul Vozila. acl-clinicalnlp 2023: 138-143 [doi]

2021

Contextual Density Ratio for Language Model Biasing of Sequence to Sequence ASR SystemsJesús Andrés-Ferrer, Dario Albesano, Puming Zhan, Paul Vozila. interspeech 2021: 2007-2011 [doi]

Retrieval-Augmented Transformer-XL for Close-Domain Dialog GenerationGiovanni Bonetta, Rossella Cancelliere, Ding Liu, Paul Vozila. flairs 2021: [doi]

2018

Scalable Wide and Deep Learning for Computer Assisted CodingMarilisa Amoia, Frank Diehl, Jesús Giménez, Joel Pinto, Raphael Schumann, Fabian Stemmer, Paul Vozila, Yi Zhang. naacl 2018: 1-7 [doi]

Efficient Language Model Adaptation with Noise Contrastive Estimation and Kullback-Leibler RegularizationJesús Andrés-Ferrer, Nathan Bodenstab, Paul Vozila. interspeech 2018: 3368-3372 [doi]

2014

Static interpolation of exponential n-gram models using features of featuresAbhinav Sethy, Stanley F. Chen, Bhuvana Ramabhadran, Paul Vozila. icassp 2014: 4878-4882 [doi]

Semi-Supervised Chinese Word Segmentation Using Partial-Label Learning With Conditional Random FieldsFan Yang, Paul Vozila. emnlp 2014: 90-98 [doi]

2013

2012

Comparison of Grapheme-to-Phoneme Methods on Large Pronunciation Dictionaries and LVCSR TasksStefan Hahn, Paul Vozila, Maximilian Bisani. interspeech 2012: 2538-2541 [doi]

Large Scale Hierarchical Neural Network Language ModelsHong-Kwang Kuo, Ebru Arisoy, Ahmad Emami, Paul Vozila. interspeech 2012: 1672-1675 [doi]

A Hierarchical Bayesian Approach for Semi-supervised Discriminative Language ModelingYik-Cheung Tam, Paul Vozila. interspeech 2012: 186-189 [doi]

2011

Improved Spoken Query Transcription Using Co-Occurrence InformationJonathan Mamou, Abhinav Sethy, Bhuvana Ramabhadran, Ron Hoory, Paul Vozila. interspeech 2011: 1473-1476 [doi]

Unsupervised Latent Speaker Language ModelingYik-Cheung Tam, Paul Vozila. interspeech 2011: 1477-1480 [doi]

2008

Automatic Editing in a Back-End Speech-to-Text SystemMaximilian Bisani, Paul Vozila, Olivier Divay, Jeff Adams. acl 2008: 114-120 [doi]

2003

Grapheme to phoneme conversion and dictionary verification using graphonemesPaul Vozila, Jeff Adams, Yuliya Lobacheva, Ryan Thomas. interspeech 2003: 2469-2472 [doi]

Sign in or sign up to see more results.

runs on WebDSL