TWiki> CSTR Web>Listen>ListenTerm3201314 (19 Aug 2014, Main.pbell1)EditAttach

-- Main.pbell1 - 27 May 2014

2013-14Term 3
02.06.14
Herman's first year talk (NB. unusual time: 10.30am)
09.06.14
No meeting (UK Speech)
16.06.14

Deep Bolzmann machines (Peter)

See also this tutorial

23.06.14

Training data selection based on context

A New Data Selection Approach for Semi-Supervised Acoustic_Modeling (Joris)

30.06.14
Trajectory analysis of speech using continuous state HMMs (Gustav)
07.07.14
Meeting postponed

14.07.14

Topics in speaker identification/diarization (Mark)

SPEAR: AN OPEN SOURCE TOOLBOX FOR SPEAKER RECOGNITION BASED ON BOB p1674-khoury.pdf

A NOVEL SCHEME FOR SPEAKER RECOGNITION USING A PHONETICALLY-AWARE DEEP NEURAL NETWORK p1714-lei.pdf

DEEP BELIEF NETWORKS FOR I-VECTOR BASED SPEAKER RECOGNITION p1719-ghahabi.pdf

21.07.14

rnn-robust-asr.pdf: RNN for ASR (Liang)

Ref: Tony Robinson's RNN Robinson_RNN.pdf

28.07.14
Talk: Spoofing attacks on speaker verification systems (Cenk Demiroglu - visitor)
04.08.14

Review of DNN adaptation (Steve)

Hank Liao (google)

Dong Yu et al (Microsoft)

George Saon et al (IBM)

Ochiai et al (NTT)

Xue et al (Microsoft)

Liu et al (Sheffield)

11.08.14

Pattern discovery in continuous speech (Herman)

Main paper using Bayesian non-parametrics: Vanhainen & Salvi

Extra reading for the above paper: Teh et al.

An auto-encoder based approach: Badino et al.

18.08.14

Adaptation of DNNs part II - iVectors George Saon et al (IBM)
Liu et al (Sheffield) + Penny's paper
25.08.14
No meeting
01.09.14
Interspeech practice talks
TBC
Deep learning for monoaural speech separation (Pawel)
TBCAn Algorithm for Training Polynomial Networks (watch this video presentation before reading) (Gustav)
  • ruslan_dbms.pdf: An efficient learning procedure for Deep Boltzmann Machines
Topic attachments
I Attachment Action Size Date Who Comment
pdfpdf A_New_Data_Selection_Approach_for_Semi-Supervised_Acoustic_Modeli-1.pdf manage 200.5 K 23 Jun 2014 - 09:29 Main.jdriesen  
pdfpdf Robinson_RNN.pdf manage 885.8 K 18 Jul 2014 - 11:54 Main.llu  
pdfpdf p1674-khoury.pdf manage 392.3 K 14 Jul 2014 - 08:05 MarkSinclair SPEAR: AN OPEN SOURCE TOOLBOX FOR SPEAKER RECOGNITION BASED ON BOB
pdfpdf p1714-lei.pdf manage 483.1 K 14 Jul 2014 - 08:06 MarkSinclair A NOVEL SCHEME FOR SPEAKER RECOGNITION USING A PHONETICALLY-AWARE DEEP NEURAL NETWORK
pdfpdf p1719-ghahabi.pdf manage 560.4 K 14 Jul 2014 - 08:06 MarkSinclair DEEP BELIEF NETWORKS FOR I-VECTOR BASED SPEAKER RECOGNITION
pdfpdf rnn-robust-asr.pdf manage 835.9 K 17 Jul 2014 - 12:53 Main.llu  
pdfpdf ruslan_dbms.pdf manage 687.9 K 15 Jun 2014 - 15:35 Main.pbell1 An efficient learning procedure for Deep Boltzmann Machines
Topic revision: r15 - 19 Aug 2014 - 11:27:44 - Main.pbell1
 
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