2011-12 | Semester1 |
05.10.11 | 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 |
12.10.11 | Planning meeting |
19.10.11 | ASR with a KL-HMM Magimai-Doss et al (Peter) |
26.10.11 | Diarization (Mark) Information Bottleneck Features for HMM/GMM Speaker Diarization of Meetings IS110316.PDF Integrated Online Speaker Clustering and Adaptation IS110311.PDF |
02.11.11 | Noisy ASR (Liang): Noise model estimation: (zhao2010comparative.pdf) Joint Uncertainty Decoding: (xu2009comarison.pdf) For more background, see Mark Gales' review (gales_noise_review10.pdf) |
09.11.11 | No meeting (Simple4All kickoff) |
16.11.11 | 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) |
23.11.11 | Deep architectures 2 (Pawel, Peter) LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION WITH CONTEXT-DEPENDENT DBN-HMMS DBN4LVCSR-TransASLP.pdf |
30.11.11 | 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 |
07.12.11 | 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 |
14.12.11 | CSTR's training setup (Mike and Peter) |
Christmas break |
I | Attachment | Action | Size![]() |
Date | Who | Comment |
---|---|---|---|---|---|---|
![]() |
Mikolov-IS110792.pdf | manage | 82.5 K | 18 Oct 2011 - 12:07 | Main.s0566164 | Magimai-Doss et al, Interspeech 2011 |
![]() |
CD-DNN-HMM-ICASSP2011.pdf | manage | 88.2 K | 22 Nov 2011 - 10:55 | Main.s1136550 | Context-Dependent hybird DNN and HMMs in LVCSR |
![]() |
sethy-0005520.pdf | manage | 102.4 K | 03 Oct 2011 - 11:02 | SteveRenals | Sethy et al, ICASSP 2011 |
![]() |
Listen-2011-12-07.ppt | manage | 120.5 K | 07 Dec 2011 - 16:56 | Main.s0566164 | Fergus' AMI recogniser slides |
![]() |
gales_noise_review10.pdf | manage | 132.2 K | 20 Oct 2011 - 09:07 | Main.llu | Gales' review |
![]() |
IS110311.PDF | manage | 157.0 K | 25 Oct 2011 - 11:27 | MarkSinclair | Integrated Online Speaker Clustering and Adaptation |
![]() |
IS110316.PDF | manage | 164.3 K | 25 Oct 2011 - 11:29 | MarkSinclair | Information Bottleneck Features for HMM/GMM Speaker Diarization of Meetings Recordings |
![]() |
zhao2010comparative.pdf | manage | 188.0 K | 20 Oct 2011 - 09:05 | Main.llu | comparison of noise estimation |
![]() |
chen-rc24970.pdf | manage | 221.8 K | 03 Oct 2011 - 11:02 | SteveRenals | Chen et al, extended version of ASRU 2009 paper |
![]() |
mohamed_hinton2011.pdf | manage | 231.0 K | 14 Nov 2011 - 11:23 | Main.s1136550 | Acoustic Modelling using DBNS |
![]() |
xu2009comarison.pdf | manage | 244.9 K | 20 Oct 2011 - 09:04 | Main.llu | comparison of jud |
![]() |
LE_ICASSP11.pdf | manage | 276.0 K | 23 Nov 2011 - 10:41 | Main.s0968719 | |
![]() |
hinton2006_deep.pdf | manage | 618.4 K | 14 Nov 2011 - 10:27 | Main.s1136550 | A fast learning algorithm for deep belief nets |
![]() |
brown-J92-4003.pdf | manage | 779.4 K | 03 Oct 2011 - 12:23 | SteveRenals | Brown et al, Computational Linguistics 1992 |
![]() |
Zweig-IS110084.pdf | manage | 892.9 K | 03 Oct 2011 - 11:00 | SteveRenals | Zweig & Chang |
![]() |
bengio2009_deep_ai.pdf | manage | 939.8 K | 14 Nov 2011 - 10:26 | Main.s1136550 | Learning Deep Architectures For AI |
![]() |
DBN4LVCSR-TransASLP.pdf | manage | 1124.2 K | 22 Nov 2011 - 14:28 | Main.s0566164 | Deep Belief Networks for LVCASR |