Speech Recognition and Machine Translation - AU-KBC Research ...

standingtopAI and Robotics

Nov 17, 2013 (3 years and 4 months ago)

64 views

Speech Recognition

and

Machine Translation

Stephan Kanthak

s.kanthak@aixplain.de

AIXPLAIN AG, Aachen, Germany

AIXPLAIN AG

Stephan Kanthak,

Speech Recognition / Machine Translation

Technology

Knowledge

Management

Machine

Translation

Speech

Recognition


Focus on Statistical Methods



Modular Software Architecture:


Speech Recognition


Machine Translation


Retrieval



Combined Applications:


Multilingual Retrieval


Retrieval of Multimedia Data


Speech
-
To
-
Speech Translation


...



Original Mission:


Speech
-
To
-
Speech Translation (for Mobile Devices)

AIXPLAIN AG

Stephan Kanthak,

Speech Recognition / Machine Translation

Speech Recognition

Search

Acoustic Models

Result

Language Model

Pronunciation Lexicon

Preprocessing

AIXPLAIN AG

Stephan Kanthak,

Speech Recognition / Machine Translation

Speech Recognition: Current Research


Feature Extraction


Phase Information


Noise Robustness


Acoustic Models


Adaptation


Maximum Entropy Models


Discriminative Training


Multilingual Acoustic Models


Language Models


Class
-
Based Backing
-
Off Models


Open Vocabulary


Search


Weighted Finite
-
State Transducer


Dialogue Management


Reinforcement Learning

AIXPLAIN AG

Stephan Kanthak,

Speech Recognition / Machine Translation

MT: Alignment Templates

Search

Lexical Models

Postprocessing

Language Model

Alignment Templates

Preprocessing

AIXPLAIN AG

Stephan Kanthak,

Speech Recognition / Machine Translation

Machine Translation: Current Research


General


Incorporate Syntactic Knowledge


Improved Alignment Models


Context
-
Free Grammars


Phrase
-
Based Models


Language Models


Class
-
Based Backing
-
Off Models


Maximum Entropy Models


Search


Stochastic Parser


Weighted Finite
-
State Transducer

AIXPLAIN AG

Stephan Kanthak,

Speech Recognition / Machine Translation

Research Projects


At Lehrstuhl für Informatik VI


Current Projects:


PF
-
Star
: Speech Translation


TransType2
: Computer Assisted Translation


LC
-
Star
: Lexica and Speech Corpora for Speech
-
To
-
Speech
Translation



Completed Projects:


TC
-
Star_P
: Preparation of TC
-
Star


CORETEX
: Core Speech Recognition Technology


VERBMOBIL II
: Speech
-
To
-
Speech Translation


Eutrans
: Speech
-
To
-
Speech Translation


ADVISOR
: Transcription of German Broadcast News and Retrieval of
Videoclips


GIZA++
: Open
-
Source Statistical Machine Translation

AIXPLAIN AG

Stephan Kanthak,

Speech Recognition / Machine Translation

Success Stories


Research Systems:


DARPA HUB4 Evaluation‘99: 4th best ASR system


VERBMOBIL: fastest and 2nd best ASR system


VERBMOBIL: best MT system


DARPA MT Evaluation‘02: best MT system


DARPA MT Evaluation‘03: 2nd best MT system



Production Systems:


Almost 200 speech recognition licenses sold in 2003


Largest installation of a pick
-
by
-
voice system in Europe in December
2003