CSC 2518 -- Spoken Language Processing

  Spring 2019

Index of this document

Contact information

Instructor: Gerald Penn
Office: PT 396B (St. George campus)
Tel: 978-7390
Back to the index

Meeting times

Lectures: T 3-5, BA 2179
Back to the index

Presented Readings


Jun Gao 22 January Learning Hard Alignments with Variational Inference ICASSP 2018
Huan Ling 22 January Efficient Dialog Policy Learning via Positive Memory Retention SLT 2018
Frank Niu 22 January
A Deep Reinforcement Learning based Multimodal Coaching Model (DCM) for Slot Filling in Spoken Language Understanding (SLU)
A New Concept of Deep Reinforcement Learning based Augmented General Sequence Tagging System

Interspeech 2018
Sean Robertson 22 January
Improving End-to-End Speech Recognition with Policy Learning
Sequence-to-Sequence ASR Optimization via Reinforcement Learning

Gavin Guan 29 January Eventness: Object Detection on Spectrograms for Temporal Localization of Audio Events ICASSP 2018
Vaibhav Saxena 29 January Robust Speech Recognition using Generative Adversarial Networks ICASSP 2018
Bret Nestor 5 February Improved ASR for Under-Resourced Languages Through Multi-Task Learning with Acoustic Landmarks Interspeech 2018
Zhewei Sun 5 February Speech2Vec: a Sequence-to-Sequence Framework for Learning Word Embeddings from Speech Interspeech 2018
Yeming Wen 5 February Spoken Language Understanding without Speech Recognition ICASSP 2018
Bai Li 12 February Automatic Characterisation of the Pronunciation of Non-native English Speakers using Phone Distance Features SLATE 2017
Patricia Thaine 12 February
Privacy-Preserving Outsourced Media Search Using Secure Sparse Ternary Codes
Differentially Private Distributed Principal Component Analysis
Sherry Wang 19 February Crepe: A Convolutional Representation for Pitch Estimation ICASSP 2018
Yizhao Wang 19 February A Single-channel Noise Reduction Filtering/Smoothing Technique in the Time Domain ICASSP 2018
Bret Nestor 26 February
Combining End-to-End and Adversarial Training for Low-Resource Speech Recognition
Unsupervised Cross-model Alignment of Speech and Text Embedding Spaces
SLT 2018
NIPS 2018
Yuwen Xiong 26 February Dialog-Context Aware End-to-End Speech Recognition SLT 2018
Gavin Guan 5 March Deep Scattering Spectrum IEEE Trans. Sig. Proc. 62(16):4114-4128, 2014
Zhewei Sun 5 March Siamese Recurrent Auto-Encoder Representation for Query-by-Example Spoken Term Detection Interspeech 2018
Bai Li 19 March Perceptually Guided Speech Enhancement Using Deep Neural Networks ICASSP 2018
Sean Robertson 19 March Multi-resolution Gammachirp Envelope Distortion Index for Intelligibility Prediction of Noisy Speech Interspeech 2018

Additional Readings for the Lectures

Title Author Publication Details
Spoken Language Processing X. Huang, A. Acero and H.-W. Hon Prentice Hall, 2001.
Discrete-Time Signal Processing, Chapters 5 and 6. J.R. Deller, Jr. , J.H.L. Hansen, and J.G. Proakis IEEE Press, 2000.
Open Finite-State Transducer Tutorial C. Allauzen, M. Jansche and M. Riley

Back to the index

Topics for this year's offering

Back to the index

Calendar of important course-related events

Date Event
Tue, 8 January First meeting
Mon, 21 January Last day to add course
Tue, 19 February would have been Reading Week, but we are still meeting!
Mon, 25 February Last day to drop course
Tue, 12 March No meeting
Tue, 2 April Last meeting
Thu, 18 April Final papers/projects due

Back to the index


Your final mark will be determined by a term paper/project, and a presentation of a paper in class.  The relative weights of these components towards the final mark are shown in the table below:

Class presentation 20%
Term paper/project 80%

Back to the index


In this space, you will find announcements related to the course. Please check this space at least weekly. Back to the index

Lecture Slides

Gerald Penn, 14 March, 2019
This web-page was adapted from the web-page for another course, created by Vassos Hadzilacos.