Home
Catalogue search
Refine your search:
Keyword:
080100 Artificial Intelligence and Image Processing (60)
Psychological Sciences (35)
FOS Computer and information sciences (26)
200400 Linguistics (23)
Computation and Language cs.CL (20)
Metapherntheorie (18)
Kognitionsforschung (16)
Parsing (14)
Metapher (13)
Spracherwerb und kognitive Entwicklung (12)
more
Creator / Publisher:
Johnson, Mark (251)
Johnson, Mark H. (105)
Macquarie University. Department of Computing (83)
Hasegawa-Johnson, Mark (45)
Lakoff, George (27)
Charman, Tony (25)
Gliga, Teodora (24)
Hasegawa-Johnson, Mark A. (24)
Charniak, Eugene (16)
Dupoux, Emmanuel (16)
more
Year
Medium:
Online (275)
Print (194)
Microfilm (1)
Type
BLLDB-Access
Search in the Catalogues and Directories
All fields
Title
Creator / Publisher
Keyword
Year
AND
OR
AND NOT
All fields
Title
Creator / Publisher
Keyword
Year
AND
OR
AND NOT
All fields
Title
Creator / Publisher
Keyword
Year
AND
OR
AND NOT
All fields
Title
Creator / Publisher
Keyword
Year
AND
OR
AND NOT
All fields
Title
Creator / Publisher
Keyword
Year
Sort by
creator [A → Z]
'
creator [Z → A]
'
publishing year ↑ (asc)
'
publishing year ↓ (desc)
'
title [A → Z]
'
title [Z → A]
'
Simple Search
Page:
1
2
3
4
5
...
24
Hits 1 – 20 of 470
1
A prospective study of associations between early fearfulness and perceptual sensitivity and later restricted and repetitive behaviours in infants with typical and elevated likelihood of Autism
Narvekar, N.
;
Carter Leno, V.
;
Pasco, G.
. - : Sage, 2022
BASE
Show details
2
Semi-supervised cycle-consistency training for end-to-end ASR using unpaired speech
Wu, Ningkai
. - 2022
Abstract:
The thesis is a replication of the work by Takaaki Hori and his colleagues (2019), which introduces a new method to train end-to-end automatic speech recognition (ASR) models using unpaired speech. In general, large amounts of paired data (speech and text) are needed to train an end-to-end automatic speech recognition system. To alleviate the problem of limited paired data, the idea of cycle-consistency losses has been proposed recently in areas such as machine translation and computer vision. In ASR, cycle-consistency training is achieved by building a reverse system, e.g., a text-to-speech system, and designing a loss based on the reconstructed signal and the original one. However, it is not straightforward to apply cycle-consistency in ASR as information would be lost in the text bottleneck. Tomoki Hayashi et al. (2018) tackled this problem via a text-to-encoder (TTE) model, which predicts encoder states extracted by a pre-trained end-to-end ASR encoder from text input. In this work, the TTE model was used as the reverse system and a loss was defined by comparing the original ASR encoder states and the reconstructed encoder states from the TTE model. Using encoder states instead of raw acoustic features as targets, the model can learn attention much faster and avoid the modeling of speaker dependencies. Our experimental results on the LibriSpeech corpus were similar to the results of Hori et al. The initial ASR and TTE models were trained with LibriSpeech 100-hour paired speech data. By applying cycle-consistency loss and retraining the speech-to-text-to-encoder chain model using one third of LibriSpeech 360-hour unpaired speech data, ASR word error rate was reduced from 25.8% to 21.7% on the LibriSpeech 5-hour test data. ; U of I Only ; Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system
Keyword:
Semi-supervised training
;
Speech recognition
URL:
http://hdl.handle.net/2142/108196
BASE
Hide details
3
Incorporating Temporal Information in Entailment Graph Mining ...
Guillou, Liane
;
de Vroe, Sander Bijl
;
Hosseini, Mohammad Javad
. - : arXiv, 2021
BASE
Show details
4
Blindness to Modality Helps Entailment Graph Mining ...
Guillou, Liane
;
de Vroe, Sander Bijl
;
Johnson, Mark
. - : arXiv, 2021
BASE
Show details
5
Implementing two-stage consent pathway in neonatal trials
Mitchell, Eleanor
;
Oddie, Sam J
;
Dorling, Jon
. - 2021
BASE
Show details
6
Integrating Lexical Information into Entity Neighbourhood Representations for Relation Prediction ...
NAACL 2021 2021
;
., Stephen
;
Johnson, Mark
. - : Underline Science Inc., 2021
BASE
Show details
7
Investigating the Mechanisms Driving Referent Selection and Retention in Toddlers at Typical and Elevated Likelihood for Autism Spectrum Disorder. ...
Gliga, Teodora
;
Skolnick, Alex
;
Liersch, Ute
. - : Apollo - University of Cambridge Repository, 2021
BASE
Show details
8
Implementing two-stage consent pathway in neonatal trials
Mitchell, Eleanor
;
Oddie, Sam J
;
Dorling, Jon
. - 2021
BASE
Show details
9
Improving multilingual speech recognition systems
Gao, Heting
. - 2021
BASE
Show details
10
Enforcing constraints for multi-lingual and cross-lingual speech-to-text systems
Ni, Junrui
. - 2021
BASE
Show details
11
Knowledge base integration in biomedical natural language processing applications
Sakakini, Tarek
. - 2021
BASE
Show details
12
Learning speech embeddings for speaker adaptation and speech understanding
Sari, Leda
. - 2021
BASE
Show details
13
Modeling phones, keywords, topics and intents in spoken languages
Chen, Wenda
. - 2021
BASE
Show details
14
Investigating the Mechanisms Driving Referent Selection and Retention in Toddlers at Typical and Elevated Likelihood for Autism Spectrum Disorder.
Gliga, Teodora
;
Skolnick, Alex
;
Liersch, Ute
. - 2021
BASE
Show details
15
Infant EEG theta modulation predicts childhood intelligence
Jones, Emily J.H.
;
Goodwin, A.
;
Orekhova, E.
. - : Nature Publishing Group, 2020
BASE
Show details
16
Neural and behavioural indices of face processing in siblings of children with autism spectrum disorder (ASD): a longitudinal study from infancy to mid-childhood
Shephard, E.
;
Milosavljevic, Bosiljka
;
Mason, Luke
. - : Elsevier, 2020
BASE
Show details
17
Speech technology for unwritten languages
Scharenborg, Odette
;
Besacier, Laurent
;
Black, Alan
...
In: ISSN: 2329-9290 ; EISSN: 2329-9304 ; IEEE/ACM Transactions on Audio, Speech and Language Processing ; https://hal.inria.fr/hal-02480675 ; IEEE/ACM Transactions on Audio, Speech and Language Processing, Institute of Electrical and Electronics Engineers, 2020, ⟨10.1109/TASLP.2020.2973896⟩ (2020)
BASE
Show details
18
Incorporating Temporal Information in Entailment Graph Mining ...
The 28th International Conference on Computational Linguistics 2020
;
Bijl de Vroe, Sander
;
Guillou, Liane
. - : Underline Science Inc., 2020
BASE
Show details
19
How Phonotactics Affect Multilingual and Zero-shot ASR Performance ...
Feng, Siyuan
;
Żelasko, Piotr
;
Moro-Velázquez, Laureano
. - : arXiv, 2020
BASE
Show details
20
That Sounds Familiar: an Analysis of Phonetic Representations Transfer Across Languages ...
Żelasko, Piotr
;
Moro-Velázquez, Laureano
;
Hasegawa-Johnson, Mark
. - : arXiv, 2020
BASE
Show details
Page:
1
2
3
4
5
...
24
Mobile view
All
Catalogues
UB Frankfurt Linguistik
25
IDS Mannheim
7
OLC Linguistik
56
UB Frankfurt Retrokatalog
0
DNB Subject Category Language
5
Institut für Empirische Sprachwissenschaft
0
Leibniz-Centre General Linguistics (ZAS)
2
Bibliographies
BLLDB
93
BDSL
0
IDS Bibliografie zur deutschen Grammatik
2
IDS Bibliografie zur Gesprächsforschung
5
IDS Konnektoren im Deutschen
0
IDS Präpositionen im Deutschen
0
IDS OBELEX meta
0
MPI-SHH Linguistics Collection
0
MPI for Psycholinguistics
44
Linked Open Data catalogues
Annohub
0
Online resources
Link directory
1
Journal directory
0
Database directory
0
Dictionary directory
0
Open access documents
BASE
272
Linguistik-Repository
0
IDS Publikationsserver
0
Online dissertations
0
Language Description Heritage
0
© 2013 - 2024 Lin|gu|is|tik
|
Imprint
|
Privacy Policy
|
Datenschutzeinstellungen ändern