Papers
A Study of Enhancement, Augmentation and Autoencoder Methods for Domain Adaptation in Distant Speech Recognition
Hao Tang, Wei-Ning Hsu, François Grondin et al.
Lattice-free State-level Minimum Bayes Risk Training of Acoustic Models
Naoyuki Kanda, Yusuke Fujita, Kenji Nagamatsu
Combining Natural Gradient with Hessian Free Methods for Sequence Training
Adnan Haider, Philip Woodland
Improved Training for Online End-to-end Speech Recognition Systems
Suyoun Kim, Michael Seltzer, Jinyu Li et al.
Comparison of Unsupervised Modulation Filter Learning Methods for ASR
Purvi Agrawal, Sriram Ganapathy
An Investigation of Mixup Training Strategies for Acoustic Models in ASR
Ivan Medennikov, Yuri Khokhlov, Aleksei Romanenko et al.
Active Learning for LF-MMI Trained Neural Networks in ASR
Yanhua Long, Hong Ye, Yijie Li et al.
Inference-Invariant Transformation of Batch Normalization for Domain Adaptation of Acoustic Models
Masayuki Suzuki, Tohru Nagano, Gakuto Kurata et al.
Investigation on the Combination of Batch Normalization and Dropout in BLSTM-based Acoustic Modeling for ASR
Li Wenjie, Gaofeng Cheng, Fengpei Ge et al.
Lightly Supervised vs. Semi-supervised Training of Acoustic Model on Luxembourgish for Low-resource Automatic Speech Recognition
Karel Veselý, Carlos Segura, Igor Szöke et al.
Data Requirements, Selection and Augmentation for DNN-based Speech Synthesis from Crowdsourced Data
Markus Toman, Geoffrey S. Meltzner, Rupal Patel
A Comparison of Speaker-based and Utterance-based Data Selection for Text-to-Speech Synthesis
Kai-Zhan Lee, Erica Cooper, Julia Hirschberg
Word Emphasis Prediction for Expressive Text to Speech
Yosi Mass, Slava Shechtman, Moran Mordechay et al.
The Perception and Analysis of the Likeability and Human Likeness of Synthesized Speech
Alice Baird, Emilia Parada-Cabaleiro, Simone Hantke et al.
Gated Convolutional Neural Network for Sentence Matching
Peixin Chen, Wu Guo, Zhi Chen et al.
Measuring the Cognitive Load of Synthetic Speech Using a Dual Task Paradigm
Avashna Govender, Simon King
Using Pupillometry to Measure the Cognitive Load of Synthetic Speech
Avashna Govender, Simon King
Investigation of Using Disentangled and Interpretable Representations for One-shot Cross-lingual Voice Conversion
Seyed Hamidreza Mohammadi, Taehwan Kim
A Hybrid Approach to Grapheme to Phoneme Conversion in Assamese
Somnath Roy, Shakuntala Mahanta
Multilingual Grapheme-to-Phoneme Conversion with Global Character Vectors
Jinfu Ni, Yoshinori Shiga, Hisashi Kawai
Joint Discriminative Embedding Learning, Speech Activity and Overlap Detection for the DIHARD Speaker Diarization Challenge
Valter Akira Miasato Filho, Diego Augusto Silva, Luis Gustavo Depra Cuozzo
The EURECOM Submission to the First DIHARD Challenge
Jose Patino, Héctor Delgado, Nicholas Evans
Diarization is Hard: Some Experiences and Lessons Learned for the JHU Team in the Inaugural DIHARD Challenge
Gregory Sell, David Snyder, Alan McCree et al.