TWiki> CSTR Web>Speak15To16 (revision 43)EditAttach

Speak! synthesis meetings schedule for 2015/2016

17.09.15 Schedule planning meeting IS15-SpeechSynthesis
24.09.15 no meeting
01.10.15 Felipe - Phase Perception & Source Filter Separation in the Phase Domain
08.10.15 Simon - Fluent Personalized Speech
15.10.15 Gustav - Random Forests for Statistical Speech Synthesis
22.10.15 Srikanth - Thesis proposal / first year review

Sam - Word Embeddings for RNN-based TTS: Wang et al (2015). Optional: Zhu et al (2015) Also optional (a very general introduction, if you find it interesting) Olah's blog post (2014).

05.11.15 Korin - Articulatory-based conversion of foreign accent using DNNs
12.11.15 Zhizheng - context clustering for DNN synthesis
19.11.15 Mirjam - How to compare TTS systems & Objective Intelligibility Assessment of TTS
26.11.15 Christophe - Vowel Enhancement for Esophageal Speech & Individuality-Preserving Spectrum Modification for Articulation Disorders using Phone Selective Synthesis
03.12.15 Srikanth - DNN-based speech synthesis for Indian languages from ASCII text & G2P conversion using LSTM networks
10.12.15 No meeting (Christmas lunch)
14.01.16 New year's planning meeting
21.01.16 Mirjam - Vocoding Challenge evaluation
28.01.16 Gustav - TTS with RVMs (Hong et al., 2015)
04.02.16 No meeting (NST in Sheffield)
11.02.16 Kazuhiro Kobayashi - Statistical singing voice conversion based on Gaussian mixture model
18.02.16 Zhizheng - DBN-based TTS features (Hu and Ling, 2016)
25.02.16 Takenori - Predicting Blizzard Challenge naturalness scores using CNNs
03.03.16 Oliver - Evaluating synthetic speech using EEG - Subjective quality ratings and physiological correlates of synthesized speech (Arndt et al. 2013) & EEG oscillations reflect task effects for the change detection in vocal emotion (Chen et al. 2015)
10.03.16 ICASSP practice session (Rasmus, Tom, Zhizheng, Korin, Gustav)
17.03.16 No meeting (ICASSP)
24.03.16 No meeting (ICASSP)
31.03.16 Post-ICASSP planning meeting
07.04.16 Post-ICASSP planning meeting redux
14.04.16 Joachim - Speech intelligibility: Weighted STOI and twin-HMM in resynthesis for STOI
21.04.16 Gustav - GANs + their application to image generation
28.04.16 Korin - Postfiltering by Ling (using DBNs & Modulation Spectrum)
05.05.16 No meeting - (SSW deadline)
12.05.16 Cassia - High-pitched excitation generation for glottal vocoding
19.05.16 Srikanth - Word embeddings for prosody
26.05.16 Felipe - Modelling unvoiced and voiced waveforms with NNs (suggested: Modelling speech waveforms with NNs)
02.06.16 No meeting (No volunteer)
09.06.16 Rasmus - A Deep Auto-Encoder Based Low-Dimensional Feature Extraction from FFT Spectral Envelopes for Statistical Parametric Speech Synthesis
16.06.16 No meeting (Tom's viva + Google Speech Summit)
23.06.16 No meeting
30.06.16 Christophe - Objective assessment of speech intelligibility for pathological voices Combining phonological and acoustic ASR-free features for pathological speech intelligibility assessment & Towards an ASR-free objective analysis of pathological speech (optional: Evaluation and assessment of speech intelligibility on pathologic voices based upon acoustic speaker models)
07.07.16 Oliver - Speaker and language factorisation (Fan et al., 2016)
Edit | Attach | Print version | History: r45 < r44 < r43 < r42 < r41 | Backlinks | Raw View | Raw edit | More topic actions...
Topic revision: r43 - 05 Jul 2016 - 10:48:44 - Main.ghenter
This site is powered by the TWiki collaboration platformCopyright © by the contributing authors. All material on this collaboration platform is the property of the contributing authors.
Ideas, requests, problems regarding TWiki? Send feedback
This Wiki uses Cookies