CSTR - Talk Schedule (Archive)

Date	Speaker
04 October 2010	Junichi Yamagishi
22 November 2010	Matthew Aylett
06 December 2010	Erich Zwyssig
21 February 2011	Partha Lal
28 February 2011	Liang Lu
07 March 2011	Sebastian Andersson
21 March 2011	Christophe Veaux
28 March 2011	Mirjam Wester
11 April 2011	David Braude
02 May 2011	Martin Tietze
06 June 2011	Oliver Watts
22 June 2015	Zhizheng Wu
29 June 2015	no talk
06 July 2015	Leimin Tian
13 July 2015	no talk (start of summer break)
20 July 2015	no talk
27 July 2015	no talk
03 August 2015	Ahmed (thesis proposal)
10 August 2015	no talk
17 August 2015	no talk (end of summer break)
20 August 2015 (Thursday)	Qiong Hu 3rd year review at 10.00 in the IMR
24 August 2015	Mireia Farrus (visitor from UPF, Spain) - speaker recognition / prosody in discourse. In the IMR
31 August 2015	Christophe Veaux
03 September 2015 (Thrusday)	Sam Ribeiro (2nd year review) at 10.00 in the IMR
03 September 2015 (Thursday)	Felipe Espic (thesis proposal) at 12.00 in the IMR
21 September 2015	Kathrin Haag (2nd year review)
23 September 2015 (Wednesday)	Mark Sinclair (pre-viva talk) at 9.00 in 4.31/4.33
28 September 2015	Máté Attila Tóth (Laslab, University of the Basque Country) Elicitation and analysis of a corpus of robust noise-induced word misperceptions in Spanish
05 October 2015	Herman Kamper (2nd year review) Learning fixed-dimensional acoustic word embeddings using side information
12 October 2015	Máté Attila Tóth Speech + noise = confusion: misperceptions arising from the interaction of speech and babble masker components.
19 October 2015	Takenori Yoshimura (Nagoya Institute of Technology) Context clustering with multiple tree structures for factor analyzed HMM-based speech synthesis
26 October 2015
02 November 2015
09 November 2015	Alan Wisler Arizona State University Acoustic and Linguistic Biomarkers for Neurological Health
16 November 2015	Matthew Aylett Speech Synthesis for the Generation of Artificial Personality
23 November 2015	Joachim Fainberg Improving Children’s Speech Recognition through Out-of-Domain Data Augmentation
30 November 2015
04 December 2015 (Friday, 10am)	David Braude, Pre-Viva talk in the IMR
07 December 2015	Ailbhe Ní Chasaide Trinity College Dublin Voice, Prosody, and Building Irish Voices
11 January 2016 Starting at 16:15	Steve Renals The MGB Challenge: Evaluating Multi-Genre Broadcast Speech Recognition
18 January 2016 in the IMR (IF-3.07)	Cassia Valentini Botinhao
29 January 2016 Friday, 9:30, IMR (IF-3.07)	Qiong Hu (DDD)
29 January 2016 Friday, 15:00, IMR (IF-3.07)	Tom Merritt (DDD)
08 February 2016 Starting at 16:15	Pawel Swietojanski (DDD)
15 February 2016	Olivier Perrotin, LIMSI
22 February 2016	Rasmus Dall Freeing the Feature: Re-examining the Linguistic Context Feature Set for HMM and DNN Synthesis
07 March 2016	Ben Krause Hessian-free optimization
14 March 2016 14:00, IMR (IF-3.07)	ICASSP practice talks
21 March 2016	(ICASSP)
28 March 2016	(Easter Monday)
11 April 2016	Siva Reddy Gangireddy Language Model Adaptation
18 April 2016 Monday, 10:00, IMR (IF-3.07)	Rasmus Dall (DDD)
09 May 2016	Herman Kamper (DDD) Unsupervised neural and Bayesian models for zero-resource speech processing
30 May 2016	Zoran Cvetkovic, King's College London Redundancy in Speech and Robustness of Automatic Speech Recognition
01 June 2016 Wednesday, 3pm	Siva Reddy Gangireddy (DDD)
06 June 2016	Leimin Tian
08 June 2016 Wednesday, 11am	CSTR general meeting
16 June 2016 Thursday, 9:30am	Tom Merritt (pre-viva talk) Overcoming the limitations of statistical parametric speech synthesis
20 June 2016	(UK Speech in Sheffield)
27 June 2016 2pm, IMR	Pawel Swietojanski (pre-viva talk)
04 July 2016
11 July 2016	Catherine Lai
19 July 2016 Tuesday, 4pm, IF-3.07	Ahmed Ali Progress with Dialectal Arabic Speech Processing
25 July 2016	Paavo Alku, Aalto University Quasi-closed phase analysis of speech and its application in vocoding and voice source estimation
26 July 2016 9:30am, Tuesday, IF-3.07	Qiong Hu (Pre-viva talk) Statistical parametric speech synthesis based on sinusoidal model
01 August 2016	Tadahiro Tanigushi, Ritsumeikan University Nonparametric Bayesian Word Discovery by a Robot: Introduction to Symbol Emergence in Robotics
26 September 2016	Joe Fruehwald, PPLS Bayesian Formant Tracking and Sound Change
03 October 2016	Korin Richmond TTS Evaluation grant proposal
24 October 2016	Hiroshi Shimodaira
07 November 2016	Simon King
14 November 2016	Ondrej Klejch (First year review)
28 November 2016	Emiru Tsunoo, Sony Corporation
December 2016	SLT (13-16 Dec)
16 January 2016	CSTR general research roundtable
23 January 2016	Amelia Gully, University of York Modelling the Vocal Tract with the 3D Dynamic Digital Waveguide Mesh
30 January 2016 12 noon, IF-4.31	Thanasis Tsanas, Usher institute Decision support tools using speech signal processing and statistical machine learning
13 February 2017 12 noon, IF-4.31	Peter Bell
27 February 2017 12 noon, IF-3.07(IMR)	Oliver Watts
13 March 2017 12:10 noon, IF-3.07(IMR)	Natsumi Koike, Nagoya Institute of Technology
23 March 2017 Thurs, 2pm, IF-3.07(IMR)	Sam Ribeiro Suprasegmental representations for the modeling of fundamental frequency in statistical parametric speech synthesis
Thurs, 4:15pm, IF-3.07(IMR)	Ahmed Ali Word Error Rate Estimation for Automatic Speech Recognition: e-WER
4-6 April 2017	ENRICH workshop
24 april 2017 4pm, IF-4.31	Zhou Yu, CMU Situated intelligent interactive systems
1 May 2017 4pm, IF-4.31	Leimin Tian (DDD) Recognizing Emotions in Spoken Dialogue with Acoustic and Lexical Cues
3 July 2017 12 noon, IF-3.07(IMR)	Carmen Magariños Iglesias, University of Vigo Language-Independent Acoustic Cloning of HTS Voices
25 July 2017 Tue 2pm, IF-3.07	Joanna Rownicka
31 July 2017 4pm, IF-4.31	Cassia Valentini Botinhao
7 August 2017 4pm, IF-4.31	John Quinn, United Nations Global Pulse
17 August 2017 Thu 2pm, IF-3.07	Ahmed Ali Draft Dissertation Defense
August 2017	Interspeech 20-24 August Matthew Aylett Junichi Yamagishi
11 September 2017	UKSpeech in Cambridge
25 September 2017	Emiru Tsunoo, Sony Story Segmentation for Broadcast Stream
2 October 2017	CSTR general meeting
09 October 2017	Matthew Aylett Bot or Not? Exploring the perception of acted, modified and synthetic speech
16 October 2017	Zack Hodari A learned emotion space for emotion recognition and emotive speech synthesis
23 October 2017	Steve Renals New projects and partnerships
30 October 2017 10:30am, IF-4.31	Leimin Tian (Viva) Recognizing Emotions in Spoken Dialogue with Acoustic and Lexical Cues
06 November 2017	Ben Krause Improving autoregressive sequence models
13 November 2017	ICMI, Glasgow
16 November 2017 2pm, IF-3.07	Martti Vainio, University of Helsinki Hierarchical representation of of speech prosody using Continuous Wavelet Transform
17 November 2017 9:30am, IF-3.07	Sam Ribeiro (Viva) Suprasegmental representations for the modeling of fundamental frequency in statistical parametric speech synthesis
20 November 2017 IF-3.07	Lauri Juvela, Aalto University Neural waveform generation methods for glottal vocoding
05 February 2018	Ondrej Klejch Learning speaker representations via speaker adaptation (second year review)
12 February 2018	Felipe Espic In the Search of the Optimal Acoustic Features for Statistical Parametric Speech Synthesis
13 February 2018 12pm, IF 3.07	Joachim Fainberg Second Year Review
26 February 2018	UCU strike day
05 March 2018	UCU strike day
12 March 2018	UCU strike day
19 March 2018	UCU strike day
26 March 2018	Truong Do Topics in Speech Translation
02 April 2018	Easter Monday
09 April 2018	Andrea Carmantini Between-Class learning for automatic speech recognition
16 April 2018	Avashna Govender First Year Review
23 April 2018	Simon Vandieken Farsi Speech Recognition for Broadcast News
14 May 2018	Simon King Speaking naturally? It depends who is listening
21 May 2018	Catherine Lai Topic and Stance in Conversational Speech
28 May 2018	Go to Professor David Dunson's Distinguished Lecture (G.07)
04 June 2018	Jon Barker, University of Sheffield The 5th CHiME speech separation and recognition challenge: Distant microphone ASR in domestic environments
11 June 2018 IF-3.07	Junichi Yamagishi The Voice Conversion Challenge 2018: Promoting Development of Parallel and Nonparallel Methods
25 June 2018	UK Speech, Dublin
02 July 2018 IF-3.07	Bertrand Higy, Italian Institute of Technology Small vocabulary speech recognition
09 July 2018	Alberto Abad, University of Lisbon Recent (on-going) work on speaker adaptive training and domain adaption for low-resource ASR
06 August 2018	Jeff Lai, Johns Hopkins University
10 September 2018	Carol Chermaz Embedding information in the speech signal
17 September 2018	Aghilas Sini, IRISA Prosodic Cues and Discursive Changes in Audiobooks
24 September 2018 IF-3.07	Shucong Zhang First Year Review
01 October 2018	Oliver Watts Speech Waveform Reconstruction using Convolutional Neural Networks with Noise and Periodic Inputs
08 October 2018	No talk Go to Kimberley Hambunchen Distinguished Lecture
15 October 2018	Joanna Rownicka CNN speech representations and acoustic model adaptation
22 October 2018	Jennifer Williams Syllable-Level Prosodic Contour Modeling for DNN TTS Synthesis
29 October 2018	ICASSP deadline
12 November 2018	Gustav Henter, KTH Cyborg speech and other controllable synthesisers: an update on past and planned research
26 November 2018	Erfan Loweimi Speech Phase Spectrum: Love It or Leave It?
03 December 2018	Zach Hodari Variation in speech synthesis: using generative models to control prosody
11 December 2018 Tue 12 noon (IF-3.07)	Jason Taylor Towards Automatic Lexicon Expansion
17 December 2018	No talk Go to Jon Oberlander Memorial Lecture
	Holidays!
28 January 2019	Jose Novoa Ilić, Universidad de Chile Automatic speech recognition for human-robot interaction scenarios
04 February 2019	Ondrej Klejch Learning to adapt - a meta-learning approach for speaker adaptation
25 February 2019	Aciel Eshky Automated synchronisation of speech and ultrasound by learning cross-modal embeddings
04 March 2019	Cassia Valentini Botinao TTS for the blind
11 March 2019	Korin Richmond EMRAPT(?)
25 March 2019	Hiroshi Shimodaira Direct estimation of F0 from speech waveforms with a value-encoder neural network
29 April 2019	Elif Kaplan, University of Groningen Are musicians at an advantage at the cocktail party?
06 May 2019	No talk (CHI, Glasgow, 4-9 May)
13 May 2019	No talk (ICASSP, Brighton, 12-17 May)
20 May 2019	Avashna Govender Second year review: Synthetic speech optimised for low cognitive load
27 May 2019	CDT Distinguished Lecture: Molham Aref, IF-G.07
03 June 2019	Erfan Loweimi Understanding and interpreting DNNs for speech recognition
10 June 2019	JinHong Lu Speech wave-form driven head motion synthesis for conversational agents
17 June 2019	Zack Hodari Using generative modelling to produce varied intonation for speech synthesis
24 June 2019	UK Speech, Birmingham
1 July 2019	Herman Kamper, Stellenbosch University Multimodal learning from images and speech
8 July 2019	Talk Postponed
11 July 2019 Tue 15:10	Jennifer Williams First year review: Simultaneous Multi-Factor Expressivity Control in Text-to-Speech Synthesis
22 July 2019	Berrak Sisman, National University of Singapore Voice Conversion
29 July 2019	Sam Ribeiro Automatic processing of ultrasound tongue imaging for child speech therapy
19 August 2019	Go to ICSA Colloquium: Romit Roy Choudhury The Internet of Acoustic Things: Ideas, Challenges, and Opportunities
22 August 2019 Thu 3pm, IF-3.07	Chau Luu Improving the speaker diarization pipeline using neural networks (First year review)
26 August 2019	Carol Chermaz Evaluating Near End Listening Enhancement Algorithms in Realistic Environments (Interspeech practice talk)
02 September 2019	Andrea Carmantini Untranscribed web audio for low resource speech recognition (Interspeech practice talk)
05 September 2019 Thu 3pm, IF-3.07	Carol Chermaz Second Year Review
09 September 2019	Jennifer Williams Disentangling Style Factors from Speaker Representations (Interspeech practice talk)
16 September 2019	Interspeech, Graz
23 September 2019	(SSW ends 22 Sep)
30 September 2019	Steve Renals Speech Technology for Emergency Medicine
07 October 2019	No talk
14 October 2019	No talk
22 October 2019 Tue 1pm IF-G.03	Sameer Bansal Low-Resource Speech Translation (Pre-Viva Talk)
28 October 2019	Oliver Watts Where do the improvements come from in sequence-to-sequence neural TTS?
04 November 2019	Jason Taylor Pronunciation Learning in Neural
11 November 2019 Mon 1:30pm Bayes 5.10	Ben Krause Flexible Neural Architectures for Sequence Modeling (Pre-Viva talk)
18 November 2019	Zack Hodari Discrete representation learning for prosody (Second Year Review)
21 November 2019 Thu 3:10pm IF-G.03	Pilar Oplustil Gallegos Training strategies for TTS with spontaneous data (First Year Review)
25 November 2019	No Talk
02 December 2019	No Talk
09 December 2019	Shucong Zhang Improving end-to-end speech recognition models (Second year review)
10 December 2019 Tue 12pm, IF-3.07	Joachim Fainberg
12 December 2019 Thu 4pm IF-G.07	Mari Ostendorf Jon Oberlander Memorial Lecture
	Holidays!
13 January 2020 Mon 4:10pm, IF-3.07	Joanna Rownicka Embeddings for SAT-DNNs and OctConvs for speech representation learning (Third Year Review)
20 January 2020	Andrea Carmantini Exploiting uncertainty for semi-supervised training of speech recognition models (First Year Review)
27 January 2020	Dimitri Palaz, Speech Graphics Speech emotion recognition for audio-driven facial animation
03 February 2020	Jacob Webber Hider/Finder/Combiner: A new approach to machine learning-based speech control
10 February 2020	No talk
17 February 2020	No talk
24 February 2020	UCU strike?
02 March 2020	UCU strike?
09 March 2020	UCU strike?
16 March 2020
23 March 2020	Jing-Xuan Zhang, University of Science and Technology of China Sequence-to-sequence based voice conversion
06 April 2020	CSTR research chat
21 April 2020 Tue 16:00	Ondrej Klejch (pre-viva talk) Learning to Adapt: Meta-Learning Approaches for Speaker Adaptation
23 April 2020 Thu 15:10	Zack Hodari Perception of prosodic variation for speech synthesis using an unsupervised discrete representation of F0
08 June 2020	Avashna Govender (DDD) Measuring the cognitive load imposed by text-to-speech synthesis
13 July 2020	Simon King Connections between speech synthesis and voice conversion
27 July 2020	Jason Fong First Year Review: Towards robust zero resource pronunciation correction of end-to-end text-to-speech
3 August 2020 at 10:00	Jennifer Williams Learning Representations for Automatic Quality Estimation and Controllable Text-to-Speech Synthesis
10 August 2020	Jacob Webber Controllable speech through adversarial representation disentanglement
17 August 2020	Chau Luu Leveraging deep speaker embedding variability factors for verification and diarization (annual review)
24 August 2020	Jinhong Lu Speech wave-form driven head motion synthesis for conversational agents (annual review)
27 August 2020 Thu 3:10pm	Jason Taylor Pronunciation Learning in Text-to-Speech Synthesis (annual review)
14 September 2020	Erfan Loweimi Raw Sign and Magnitude Spectra for Multi-head Acoustic Modelling
21 September 2020 Mon 10:00am	Shucong Zhang Investigating the usefulness of self-attention for speech recognition (Annual review)