TWiki> CSTR Web>Listen>ListenSemester1201112 (07 Dec 2011, Main.s0566164)EditAttach


Language models (Steve) - Model M

Zweig and Chang, Personalising Model M, Interspeech 2011

Chen et al, Scaling shrinkage-based LMs, Extended version of ASRU-2009

Sethy et al, Distributed training of Model M, ICASSP 2011

Brown et al, Class-based n-grams, Computational Linguistics 1992

Planning meeting

ASR with a KL-HMM Magimai-Doss et al (Peter)


Diarization (Mark)

Information Bottleneck Features for HMM/GMM Speaker Diarization of Meetings


Integrated Online Speaker Clustering and Adaptation



Noisy ASR (Liang):

Noise model estimation: (zhao2010comparative.pdf)

Joint Uncertainty Decoding: (xu2009comarison.pdf)

For more background, see Mark Gales' review (gales_noise_review10.pdf)

09.11.11No meeting (Simple4All kickoff)

Deep architectures 1 (Pawel, Steve)

Acoustic Modelling using Deep Belief Networks (mohamed_hinton2011.pdf)

Optional reading for broader background on deep networks:

Hinton, et al. A fast learning algorithm for deep belief networks (hinton2006_deep.pdf)

Yoshua Bengio, Learning Deep Architectures for AI (bengio2009_deep_ai.pdf)


Deep architectures 2 (Pawel, Peter)



ASR of Lombard speech (Cassia)

Unsupervised equalization of Lombard effect for speech recognition in noisy adverse environments LE_IEEETrans.pdf

UT-SCOPE: Towards LVCSR under Lombard effect induced by varying types and levels of noisy background LE_ICASSP11.pdf


NB change of time - probably 3pm.

CSTR's recognition setup (Fergus)

Background reading:

IEEE Transactions paper (in draft) on the AMIDA RT07 and RT09 systems: Hain et al., Transcribing meetings with the AMIDA systems

We won't be going through the paper in detail, but there will be some slides on the present state of the system and how to obtain and use it.

Here are the slides: Listen-2011-12-07.ppt

CSTR's training setup (Mike and Peter)
Christmas break

Topic attachments
ISorted ascending Attachment Action Size Date Who Comment
pdfpdf CD-DNN-HMM-ICASSP2011.pdf manage 88.2 K 22 Nov 2011 - 10:55 Main.s1136550 Context-Dependent hybird DNN and HMMs in LVCSR
pdfpdf DBN4LVCSR-TransASLP.pdf manage 1124.2 K 22 Nov 2011 - 14:28 Main.s0566164 Deep Belief Networks for LVCASR
pdfPDF IS110311.PDF manage 157.0 K 25 Oct 2011 - 11:27 MarkSinclair Integrated Online Speaker Clustering and Adaptation
pdfPDF IS110316.PDF manage 164.3 K 25 Oct 2011 - 11:29 MarkSinclair Information Bottleneck Features for HMM/GMM Speaker Diarization of Meetings Recordings
pdfpdf LE_ICASSP11.pdf manage 276.0 K 23 Nov 2011 - 10:41 Main.s0968719  
pdfpdf Mikolov-IS110792.pdf manage 82.5 K 18 Oct 2011 - 12:07 Main.s0566164 Magimai-Doss et al, Interspeech 2011
pdfpdf Zweig-IS110084.pdf manage 892.9 K 03 Oct 2011 - 11:00 SteveRenals Zweig & Chang
pdfpdf bengio2009_deep_ai.pdf manage 939.8 K 14 Nov 2011 - 10:26 Main.s1136550 Learning Deep Architectures For AI
pdfpdf brown-J92-4003.pdf manage 779.4 K 03 Oct 2011 - 12:23 SteveRenals Brown et al, Computational Linguistics 1992
pdfpdf chen-rc24970.pdf manage 221.8 K 03 Oct 2011 - 11:02 SteveRenals Chen et al, extended version of ASRU 2009 paper
pdfpdf gales_noise_review10.pdf manage 132.2 K 20 Oct 2011 - 09:07 Main.llu Gales' review
pdfpdf hinton2006_deep.pdf manage 618.4 K 14 Nov 2011 - 10:27 Main.s1136550 A fast learning algorithm for deep belief nets
pdfpdf mohamed_hinton2011.pdf manage 231.0 K 14 Nov 2011 - 11:23 Main.s1136550 Acoustic Modelling using DBNS
pdfpdf sethy-0005520.pdf manage 102.4 K 03 Oct 2011 - 11:02 SteveRenals Sethy et al, ICASSP 2011
pdfpdf xu2009comarison.pdf manage 244.9 K 20 Oct 2011 - 09:04 Main.llu comparison of jud
pdfpdf zhao2010comparative.pdf manage 188.0 K 20 Oct 2011 - 09:05 Main.llu comparison of noise estimation
pptppt Listen-2011-12-07.ppt manage 120.5 K 07 Dec 2011 - 16:56 Main.s0566164 Fergus' AMI recogniser slides
Topic revision: r17 - 07 Dec 2011 - 16:57:20 - Main.s0566164
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