From speech to letters - using a novel neural network architecture for grapheme based ASR
- Standort
-
Deutsche Nationalbibliothek Frankfurt am Main
- Umfang
-
Online-Ressource
- Sprache
-
Englisch
- Anmerkungen
-
In: 2009 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU 2009), 13 November - 17 December 2009, Merano, Italy, S. 376-380
- Klassifikation
-
Informatik
- Ereignis
-
Veröffentlichung
- (wo)
-
Augsburg
- (wer)
-
Universität Augsburg
- (wann)
-
2009
- Ereignis
-
Veröffentlichung
- (wo)
-
Piscataway, NJ
- (wer)
-
IEEE
- (wann)
-
2009
- Urheber
- Beteiligte Personen und Organisationen
-
Riccardi, Giuseppe
De Mori, Renato
Di Fabbrizio, Giuseppe
- DOI
-
10.1109/ASRU.2009.5373257
- URN
-
urn:nbn:de:bvb:384-opus4-766084
- Rechteinformation
-
Der Zugriff auf das Objekt ist unbeschränkt möglich.
- Letzte Aktualisierung
-
15.08.2025, 07:37 MESZ
Datenpartner
Dieses Objekt wird bereitgestellt von:
Deutsche Nationalbibliothek. Bei Fragen zum Objekt wenden Sie sich bitte an den Datenpartner.
Deutsche Nationalbibliothek. Bei Fragen zum Objekt wenden Sie sich bitte an den Datenpartner.
Beteiligte
- Eyben, Florian
- Wöllmer, Martin
- Schuller, Björn
- Graves, Alex
- Riccardi, Giuseppe
- De Mori, Renato
- Di Fabbrizio, Giuseppe
- Universität Augsburg
- IEEE
Entstanden
- 2009
Ähnliche Objekte (12)
Combining long short-term memory and dynamic Bayesian networks for incremental emotion-sensitive artificial listening
A multitask approach to continuous five-dimensional affect sensing in natural speech
String-based audiovisual fusion of behavioural events for the assessment of dimensional affect
Spoken term detection with Connectionist Temporal Classification: a novel hybrid CTC-DBN decoder
Context-sensitive machine learning for intelligent human behavior analysis
Robust vocabulary independent keyword spotting with graphical models
Computational assessment of interest in speech - facing the real-life challenge
OpenEAR - introducing the Munich open-source emotion and affect recognition toolkit
Prosodic, spectral or voice quality? Feature type relevance for the discrimination of emotion pairs
Improving keyword spotting with a tandem BLSTM-DBN architecture
Data-driven clustering in emotional space for affect recognition using discriminatively trained LSTM networks
Bidirectional LSTM networks for context-sensitive keyword detection in a cognitive virtual agent framework
Combining long short-term memory and dynamic Bayesian networks for incremental emotion-sensitive artificial listening
A multitask approach to continuous five-dimensional affect sensing in natural speech
String-based audiovisual fusion of behavioural events for the assessment of dimensional affect
Spoken term detection with Connectionist Temporal Classification: a novel hybrid CTC-DBN decoder
Context-sensitive machine learning for intelligent human behavior analysis
Robust vocabulary independent keyword spotting with graphical models
Computational assessment of interest in speech - facing the real-life challenge
OpenEAR - introducing the Munich open-source emotion and affect recognition toolkit
Prosodic, spectral or voice quality? Feature type relevance for the discrimination of emotion pairs
Improving keyword spotting with a tandem BLSTM-DBN architecture
Data-driven clustering in emotional space for affect recognition using discriminatively trained LSTM networks
Bidirectional LSTM networks for context-sensitive keyword detection in a cognitive virtual agent framework
Combining long short-term memory and dynamic Bayesian networks for incremental emotion-sensitive artificial listening
A multitask approach to continuous five-dimensional affect sensing in natural speech
String-based audiovisual fusion of behavioural events for the assessment of dimensional affect
Spoken term detection with Connectionist Temporal Classification: a novel hybrid CTC-DBN decoder
Context-sensitive machine learning for intelligent human behavior analysis
Robust vocabulary independent keyword spotting with graphical models
Computational assessment of interest in speech - facing the real-life challenge
OpenEAR - introducing the Munich open-source emotion and affect recognition toolkit
Prosodic, spectral or voice quality? Feature type relevance for the discrimination of emotion pairs
Improving keyword spotting with a tandem BLSTM-DBN architecture
Data-driven clustering in emotional space for affect recognition using discriminatively trained LSTM networks