phonological constituents from speech
Báo cáo khoa học: "From Information Structure to Intonation: A Phonological Interface for Concept-to-Speech" pot
Ngày tải lên :
08/03/2014, 06:20
...
tours for German, in Proc. of Eurospeech 97,
Rhodes, Greece, 1:307-10, 1997.
Prevost S., Steedman M.: Specifying Intonation
from Context for Speech Synthesis, Speech
Communication, 15:139-153, ... Synthe-
sizer Interface in Concept-to -Speech, in Proc.
of Eurospeech 95, Madrid, 2:1223-26, 1995.
Niklfeld G., Alter K.: Covering prosody in
concept-to -speech via an extended two-level-
phonology ... Morgan Kaufmann,
San Mateo, CA, pp.1024-1030, 1991.
1045
From Information Structure to Intonation: A Phonological
Interface for Concept-to -Speech
Hannes Pirker, Georg Niklfeld, Johannes Matiasek...
- 5
- 498
- 0
Tài liệu Báo cáo khoa học: "Improving Automatic Speech Recognition for Lectures through Transformation-based Rules Learned from Minimal Data" ppt
Ngày tải lên :
20/02/2014, 07:20
... 2-7 August 2009.
c
2009 ACL and AFNLP
Improving Automatic Speech Recognition for Lectures through
Transformation-based Rules Learned from Minimal Data
Cosmin Munteanu
∗†
∗
National Research Council ... can be used to correct noisy
speech recognition transcripts in the lec-
ture domain with an average word error
rate reduction of 12.9%. Our method is
distinguished from earlier related work by
its ... the per-
fect transcript. This reduced WER from 41% to
35% on a corpus of train dispatch dialogues. Oth-
ers combine the transcripts or word lattices (from
which transcripts are extracted) of two...
- 9
- 427
- 0
Tài liệu Báo cáo khoa học: "Deriving an Ambiguous Word’s Part-of-Speech Distribution from Unannotated Text" doc
Ngày tải lên :
20/02/2014, 12:20
... 2007.
c
2007 Association for Computational Linguistics
Deriving an Ambiguous Word’s Part-of -Speech Distribution
from Unannotated Text
Reinhard Rapp
Universitat Rovira i Virgili
Pl. Imperial Tarraco, ...
Abstract
A distributional method for part-of -speech
induction is presented which, in contrast
to most previous work, determines the
part-of -speech distribution of syntacti-
cally ambiguous ... vec-
tors. As can be seen from human performance, in
almost all cases the local context of a syntactically
ambiguous word is sufficient to disambiguate its
part of speech.
The core assumption...
- 4
- 389
- 0
Tài liệu Báo cáo khoa học: "Inferring Selectional Preferences from Part-Of-Speech N-grams" doc
Ngày tải lên :
22/02/2014, 03:20
... random from the test corpus. Rooth
et al. (1999) and Erk et al. (2010) chose such
pairs from a training corpus to ensure that it
contained the target t. In contrast, choosing pairs
from an ... dependency-based space.
381
Figure 1: Overview of PONG.
From the labeled corpus, PONG extracts abstract mappings from POS N-grams to relations.
From the unlabeled corpus, PONG estimates POS N-gram ... preferences using part-of -speech
(POS) N-grams. From a corpus labeled with
grammatical dependencies, PONG learns the
distribution of word relations for each POS
N-gram. From the much larger but...
- 10
- 375
- 0
Báo cáo khoa học: "A Cost Sensitive Part-of-Speech Tagging: Differentiating Serious Errors from Minor Errors" pptx
Ngày tải lên :
07/03/2014, 18:20
... 2012.
c
2012 Association for Computational Linguistics
A Cost Sensitive Part-of -Speech Tagging:
Differentiating Serious Errors from Minor Errors
Hyun-Je Song
1
Jeong-Woo Son
1
Tae-Gil Noh
2
Seong-Bae ... International Confer-
ence on Machine Learning. pp. 282–289.
Christopher D. Manning. 2011. Part-of -Speech Tagging
from 97% to 100%: Is It Time for Some Linguistics?.
In Proceedings of the 12th International ... Chicago
{hjsong,jwson,tgnoh}@sejong.knu.ac.kr sbpark@uic.edu sjlee@knu.ac.kr
Abstract
All types of part-of -speech (POS) tagging er-
rors have been equally treated by existing tag-
gers. However, the errors...
- 10
- 406
- 0
Báo cáo khoa học: "A Practical Solution to the Problem of Automatic Part-of-Speech Induction from Text" pdf
Ngày tải lên :
08/03/2014, 04:22
... 2. Computed parts of speech for each word.
5 Summary and Conclusions
This work was inspired by previous work on word
sense induction. The results indicate that part of
speech induction is ... Proceedings
of ACL (Companion Volume), Barcelona, 195-198.
Schütze, Hinrich (1993). Part-of -speech induction from
scratch. Proceedings of ACL, Columbus, 251-258.
0.8
0.4
0.0
... centroids becomes too low.
This way an ambiguous word is assigned to several
parts of speech, starting from the most common
and proceeding to the least common. Figure 1 il-
lustrates this process....
- 4
- 433
- 0
Báo cáo khoa học: "Acquiring a Lexicon from Unsegmented Speech" potx
Ngày tải lên :
08/03/2014, 07:20
...
language acquisition and computer speech
recognition.
1 Introduction
We are interested in how a lexicon of discrete words
can be acquired from continuous speech, a prob-
lem fundamental both ... Acquiring a Lexicon from Unsegmented Speech
Carl de Marcken
MIT Artificial Intelligence Laboratory
545 Technology Square, ... problem as induction from phone se-
quences rather than acoustic pressure, and assume
that learning takes place in an environment where
simple semantic representations of the speech intent
are...
- 3
- 315
- 0
Báo cáo khoa học: "Person Identification from Text and Speech Genre Samples" ppt
Ngày tải lên :
17/03/2014, 22:20
...
communication” nature is quite different from
the other text genres of emails, essays and blogs.
Identifying a person in one speech genre after
training with the other speech genre had lower
accuracies ... features
are denoted feature set L.
From the original 24 participants’ documents
and the new 7 participants’ documents from
Phase II, we aggregated all samples from all ge-
nres and computed the ...
336
5.4 Predict Communicant in a Speech Ge-
nre Given Information on the Other
One interesting experiment used one speech ge-
nre for training, and the other speech genre for
testing. The results...
- 9
- 330
- 0
Formulas from combustion Analysis
Ngày tải lên :
22/08/2012, 09:18
... Tìm công thc phân t formulas from combustion analysis
Trang 3
tìm c t s ti gin bng cách chia các s mol cho s mol ... xác nh khi lng và s mol ca cacbon, hydro t CO
2
và H
2
O
Tìm công thc phân t formulas from combustion analysis
Trang 1
Tìm công thc phân t t phn ng
t cháy
(The Young Vietnamese ... H
2
O x
2
1 HO
18.01 g
mol
x
2
2 H
1 mol H O
mol
= 0.1230 mol H
Tìm công thc phân t formulas from combustion analysis
Trang 2
có c t s ti gin, chia s mol ca mi nguyên t cho s...
- 4
- 585
- 0