TWiki
>
CSTR Web
>
CSTR-ASR
>
ASRPlan2014
(11 Jun 2014,
SteveRenals
)
E
dit
A
ttach
IWSLT
English ASR
Acoustic model (Peter)
Base model: TED; tandem, hybrid, spec+MFCC/PLP features; MLAN (switchboard/AMI/BBC); HTK+KALDI
Contrasts: increased base training data (late stage); Pawel-adaptation
Language model
slightly more in-domain + b/g model - n-grams (Fergus)
RNNs - Andrew Liu's training and decoding (Toms)
Segmentation (Mark)
refined system; +NNs
Italian/German ASR
revisit light supervision (alllow noisier matches)
Downloaded TED talks (DE/IT) - look into commercial transcription
German braodacast from RBM
Euronews, Europarl
ask Pervoice for IT broadcast subtitles
LM data following IWSLT links
BBC/Sky
BBC
Waiting on Cam 1-week-seg (23 June?)
Dry run on existing seg
LM on subtitle data - 3/4-gram (20 June) + gigaword/news-crawl
try kenlm
Sky
waiting for raw subtitle files, should match audio time better
Sky News transcriptions
dev and eval sets being prepared
--
SteveRenals
- 11 Jun 2014
E
dit
|
A
ttach
|
P
rint version
|
H
istory
: r1
|
B
acklinks
|
R
aw View
|
Ra
w
edit
|
M
ore topic actions
Topic revision: r1 - 11 Jun 2014 - 14:03:17 -
SteveRenals
CSTR
CSTR Web
CSTR Web Home
Changes
Index
Search
Webs
ANC
Android4EDU
BDEteam
CSTR
CogsciTeach
ComputingStrategy
DICE
DReaM
DSOClets
DatabaseGroup
DistributedComputing
DiyDice
Dizzy
DocsByUsers
ECCOModelling
ECHOES
EyeTracking
F4K
FC3upgrade
Ftlwiki
INFBase
Inf2aWiki
JastProject
LINCS
LTG
MATCH
MLforNLP
Main
MusIC
PG
Prism
RaviProgress
SDP
SDPGroup1
SDPGroup10
SDPGroup3
SDPGroup5
SDPGroup6
SDPGroup7
SDPGroup8
SDPGroup9
SEOC
Sandbox
SecurityProgramme
SelfManaged
Seminars
StudioLab
TFlex
TWiki
TheBeast
Ug30708
Vademecum
VerbClasses
WebExp
YouTute
My links
My home page
edit
Copyright © 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