Magne Hallstein Johnsen
Bakgrunn og aktiviteter
Vitenskapelig, faglig og kunstnerisk arbeid
Et utvalg av nyere tidsskriftspublikasjoner, kunstneriske produksjoner, bok, inklusiv bokdeler og rapport-del. Se alle publikasjoner i databasen
Tidsskriftspublikasjoner
- (2012) Joint Feature And Model Training For Minimum Detection Errors Applied To Speech Subword Detection. Machine Learning for Signal Processing.
- (2011) Optimized Feature Extraction and HMMs in Subword Detectors. Proceedings of the International Conference on Spoken Language Processing.
- (2010) Penalized Logistic Regression with HMM Log-Likelihood Regressors for Speech Recognition. IEEE Transactions on Audio, Speech, and Language Processing. vol. 18 (6).
- (2008) Cepstral Domain Voice Activity Detection for Improved Noise Modeling in MMSE Feature Enhancement for ASR. Proceedings of the International Conference on Spoken Language Processing.
- (2007) Variational Bayesian Learning of Speech GMMs for Feature Enhancement based on Algonquin. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing.
- (2005) Joint Bayesian Predictive Classification and Parallel Model Combination for Robust Speech Recognition. Eurospeech : Proceedings of the European Conference on Speech Communication and Technology.
- (2003) A Norwegian spoken dialogue system for bus travel information - Alternative dialogue structures and evaluation of a system driven version. Telektronikk. vol. 99.
Del av bok/rapport
- (2009) Automatic evaluation of quantity contrast in non-native Norwegian speech. ISCA Workshop on Speech and Language Technology in Education 2009 (SLaTE 2009).
- (2008) Joint Optimization of Event Detectors and Evidence Merger for Continuous Speech Recognition. Proceedings ISCA ITRW on Speech Analysis and Processing for Knowledge Discovery.
- (2006) Log Likelihood Ratio Based Annotation Verification of a Norwegian Speech Synthesis Database. Proceedings of the 7th Nordic Signal Processing Symposium (NORSIG 2006).
Rapport/avhandling
- (1999) Nasjonalt korpus for språkteknologi - forprosjekt. 1999.
- (1995) Talegjenkjenning II. 1995.
- (1995) Talegjenkjenning for teksting av direktesendte programmer - en studie. 1995.
- (1987) Gjenkjenning av isolerte ord basert på kontinuerlige, skjulte Markov-modeller. 1987.