Statistical Machine Translation for Speech: A Perspective on Structures, Learning, and Decoding

In this paper, we survey and analyze state-of-the-art statistical machine translation (SMT) techniques for speech translation (ST). We review key learning problems, and investigate essential model structures in SMT, taking a unified perspective to reveal both connections and contrasts between automa...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings of the IEEE Jg. 101; H. 5; S. 1180 - 1202
1. Verfasser: Zhou, Bowen
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York IEEE 01.05.2013
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Automata
Consolidation
Context awareness
Decoding
Discriminative training
finite-state transducer (FST)
Formalism
graph
hypergraph
Information processing
Learning
Machine translation
Speech
Speech processing
speech translation (ST)
Statistical learning
statistical machine translation (SMT)
Synchronous
synchronous context-free grammar (SCFG)
Syntax
Training
Transducers
Translations
Viterbi algorithm
Viterbi search
ISSN:0018-9219, 1558-2256
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In this paper, we survey and analyze state-of-the-art statistical machine translation (SMT) techniques for speech translation (ST). We review key learning problems, and investigate essential model structures in SMT, taking a unified perspective to reveal both connections and contrasts between automatic speech recognition (ASR) and SMT. We show that phrase-based SMT can be viewed as a sequence of finite-state transducer (FST) operations, similar in spirit to ASR. We further inspect the synchronous context-free grammar (SCFG)-based formalism that includes hierarchical phrase-based and many linguistically syntax-based models. Decoding for ASR, FST-based, and SCFG-based translation is also presented from a unified perspective as different realizations of the generic Viterbi algorithm on graphs or hypergraphs. These consolidated perspectives are helpful to catalyze tighter integrations for improved ST, and we discuss joint decoding and modeling toward coupling ASR and SMT.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ObjectType-Article-2
ObjectType-Feature-1
content type line 23
ISSN:0018-9219
1558-2256
DOI:10.1109/JPROC.2013.2249491