DE eng

Search in the Catalogues and Directories

Page: 1 2 3 4
Hits 1 – 20 of 70

1
Automatic Dialect Density Estimation for African American English ...
BASE
Show details
2
DIALKI: Knowledge Identification in Conversational Systems through Dialogue-Document Contextualization ...
BASE
Show details
3
Dialogue State Tracking with a Language Model using Schema-Driven Prompting ...
BASE
Show details
4
A Controllable Model of Grounded Response Generation ...
BASE
Show details
5
Neural Models for Integrating Prosody in Spoken Language Understanding
Tran, Trang. - 2020
BASE
Show details
6
Automatic Analysis of Language Use in K-16 STEM Education and Impact on Student Performance
Nadeem, Farah. - 2020
BASE
Show details
7
Asynchronous Speech Recognition Affects Physician Editing of Notes
Lybarger, Kevin J.; Ostendorf, Mari; Riskin, Eve. - : Georg Thieme Verlag KG, 2018
BASE
Show details
8
Low-Rank RNN Adaptation for Context-Aware Language Modeling
Jaech, Aaron. - 2018
BASE
Show details
9
Parsing Speech: A Neural Approach to Integrating Lexical and Acoustic-Prosodic Information ...
BASE
Show details
10
Effective Use of Cross-Domain Parsing in Automatic Speech Recognition and Error Detection
Marin, Marius. - 2015
Abstract: Thesis (Ph.D.)--University of Washington, 2015 ; Automatic speech recognition (ASR), the transcription of human speech into text form, is used in many settings in our society, ranging from customer service applications to personal assistants on mobile devices. In all such settings it is important for the system to know when it is making errors, so that it may ask the user to rephrase or restate their previous utterance. Such errors are often syntactically anomalous. The primary goal of this thesis is to find novel uses of parsing for automatic detection and correction of ASR errors. We start by developing a framework for ASR rescoring and automatic error detection leveraging syntactic parsing in conjunction with a maximum entropy classifier, and find that parsing helps with error detection, even when the parser is trained on out-of-domain data. In particular, features capturing parser reliability are used to improve the detection of out-of-vocabulary (OOV) and name errors. However, parsers trained on out-of-domain treebanks do not provide any benefit to ASR rescoring. This observation motivates our work on domain adaptation of parsing, with the objective of directly improving both transcription accuracy and error detection. We develop two weakly supervised domain adaptation methods which use error labels, but no hand-annotated parses: a self-training approach to directly improve the probabilistic context-free grammar (PCFG) model used in parsing, as well as a novel model combination method using a discriminative log-linear model to augment the generative PCFG. We apply both methods to ASR rescoring and error detection tasks. We find that self-training improves the ability of our parser to select the correct ASR hypothesis. The log-linear adaptation improves both OOV and name error detection tasks, and self-training performed after log-linear adaptation further improves the reliability of the parser, while producing smaller, faster models. Finally, motivated by empirical observations that the presence of names in an utterance is often indicated by words located far apart from the names themselves, we develop a general long-distance phrase pattern learning algorithm using word-level semantic similarity measures, and apply it to the problem of name error detection. This novel feature learning method leads to more robust classification, both when used independently of parsing, and in conjunction with parse features.
Keyword: Electrical engineering; feature learning; machine learning; parsing; speech recognition
URL: http://hdl.handle.net/1773/33149
BASE
Hide details
11
Automatic Characterization of Text Difficulty
Medero, Julie. - 2014
BASE
Show details
12
Data Selection for Statistical Machine Translation
BASE
Show details
13
Graph-based query strategies for active learning
In: Institute of Electrical and Electronics Engineers. IEEE transactions on audio, speech and language processing. - New York, NY : Inst. 21 (2013) 2, 260-269
OLC Linguistik
Show details
14
Rank and Sparsity in Language Processing
BASE
Show details
15
Joint reranking of parsing and word recognition with automatic segmentation
In: Computer speech and language. - Amsterdam [u.a.] : Elsevier 26 (2012) 1, 1-19
BLLDB
OLC Linguistik
Show details
16
Graph-based Algorithms for Lexical Semantics and its Applications
Wu, Wei. - 2012
BASE
Show details
17
Expected dependency pair match: predicting translation quality with expected syntactic structure
In: Machine translation. - Dordrecht [u.a.] : Springer Science + Business Media 23 (2010) 2-3, 169-179
BLLDB
OLC Linguistik
Show details
18
A machine learning approach to reading level assessment
In: Computer speech and language. - Amsterdam [u.a.] : Elsevier 23 (2009) 1, 89-106
OLC Linguistik
Show details
19
A machine learning approach to reading level assessment
In: Computer speech and language. - Amsterdam [u.a.] : Elsevier 23 (2009) 1, 89-106
BLLDB
OLC Linguistik
Show details
20
Improving robustness of MLLR adaptation with speaker-clustered regression class trees
In: Computer speech and language. - Amsterdam [u.a.] : Elsevier 23 (2009) 2, 176-199
BLLDB
OLC Linguistik
Show details

Page: 1 2 3 4

Catalogues
4
0
17
0
0
1
0
Bibliographies
27
0
0
0
0
0
0
0
1
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
34
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern