SPEECH@SV

Publications

2017

  • Bing Liu, Tong Yu, Ian Lane, and Ole Mengshoel, "Customized Nonlinear Bandits for Online Response Selection in Neural Conversation Models", in AAAI 2018.
  • Bing Liu, Gokhan Tur, Dilek Hakkani-Tur, Pararth Shah, and Larry Heck, "End-to-End Optimization of Task-Oriented Dialogue Model with Deep Reinforcement Learning", (under review) in NIPS 2017 Workshop on Conversational AI.
  • Bing Liu and Ian Lane, "Multi-Domain Adversarial Learning for Slot Filling in Spoken Language Understanding", (under review) in ICASSP 2018.
  • Suyoun Kim, Michael L. Seltzer, "Towards Language-universal end-to-end speech recognition", (under review) in ICASSP 2018.
  • Bhiksha Raj, Benjamin Elizalde, Ankit Shah, Rohan Badlani, Anurag Kumar. Never-Ending Learner of Sounds”, in NIPS Workshop Machine Learning for Audio ML4Audio 2017.
  • Suyoun Kim, Michael L. Seltzer, Jinyu Li, Rui Zhao, "Improved training for online end-to-end speech recognition systems", (under review) in ICASSP 2018.
  • Shinji Watanabe, Takaaki Hori, Suyoun Kim, John R Hershey, Tomoki Hayashi, "Hybrid CTC/Attention Architecture for End-to-End Speech Recognition", IEEE Journal of Selected Topics in Signal Processing, 2017.
  • Bing Liu and Ian Lane, "Iterative Policy Learning in End-to-End Trainable Task-Oriented Neural Dialog Models", in ASRU 2017.
  • Abelino Jimenez, Benjamin Elizalde and Bhiksha Raj, "DCASE 2017 Task 1: Acoustic Scene Classification Using Shift-Invariant Kernels and Random Features", in IEEE Detection and Classification of Acoustic Scenes and Events Workshop 2017 (DCASE2017).
  • A. Mesaros, T. Heittola, A. Diment, B. Elizalde, A. Shah, E. Vincent, B. Raj, and T. Virtanen, "IEEE DCASE 2017 challenge setup: tasks, datasets and baseline system", in IEEE Detection and Classification of Acoustic Scenes and Events Workshop 2017 (DCASE2017).
  • Akshay Chandrashekaran and Ian Lane, "Speeding up Hyper-parameter Optimization by Extrapolation of Learning Curves using Previous Builds", in ECML 2017
  • Akshay Chandrashekaran and Ian Lane, "Hierarchical Constrained Bayesian Optimization for Joint Feature, Acoustic Model and Decoder Parameter Optimization", in Interspeech 2017
  • Bing Liu and Ian Lane, "An End-to-End Trainable Neural Network Model with Belief Tracking for Task-Oriented Dialog", in INTERSPEECH 2017. (Bibtex)
  • Anurag Kumar, Benjamin Elizalde, Bhiksha Raj. "Audio Content based Geotagging in Multimedia", in INTERSPEECH 2017.
  • Benjamin Elizalde, Ankit Shah, Rohan Badlani, Siddarth Dalmia, Min Lee, Bhiksha Raj, Ian Lane, "An Approach for Self-Training Audio Event Detectors Using Web Data", in EUSIPCO 2017.
  • Suyoun Kim, Takaaki Hori and Shinji Watanabe, "Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learning", in ICASSP 2017.
  • Bing Liu and Ian Lane, "Dialog Context Language Modeling with Recurrent Neural Networks", in ICASSP 2017. (Bibtex)

2016

2015

2014

2013

  • Jonas Gehring, Wonkyum Lee, Kevin Kilgour, Ian Lane, Yaije Miao and Alex Waibel, "Modular Combination of Deep Neural Networks for Acoustic Modeling," in INTERSPEECH 2013.
  • Ankur Gandhe, Long Qin, Florian Metze, Alexander Rudnicky, Ian Lane, and Matthias Eck, "Using web text to improve keyword spotting in speech," in ASRU 2013.

2012