Hynek Hermansky - researchr alias

researchr

You are not signed in
Sign in
Sign up

2011

Analysis of MLP-Based Hierarchical Phoneme Posterior Probability EstimatorJoel Pinto, Garimella S. V. S. Sivaram, Mathew Magimai-Doss, Hynek Hermansky, Hervé Bourlard. taslp, 19(2):225-241, 2011. [doi]

Multilayer perceptron with sparse hidden outputs for phoneme recognitionGarimella S. V. S. Sivaram, Hynek Hermansky. icassp 2011: 5336-5339 [doi]

MLP based phoneme detectors for Automatic Speech RecognitionSamuel Thomas, Patrick Nguyen, Geoffrey Zweig, Hynek Hermansky. icassp 2011: 5024-5027 [doi]

Speech recognitionwith segmental conditional random fields: A summary of the JHU CLSP 2010 Summer WorkshopGeoffrey Zweig, Patrick Nguyen, Dirk Van Compernolle, Kris Demuynck, Les E. Atlas, Pascal Clark, Gregory Sell, Meihong Wang, Fei Sha, Hynek Hermansky, Damianos Karakos, Aren Jansen, Samuel Thomas, Sivaram G. S. V. S., Sam Bowman, Justine T. Kao. icassp 2011: 5044-5047 [doi]

2010

Fully integrated 500uW speech detection wake-up circuitTobi Delbrück, Thomas Koch, Raphael Berner, Hynek Hermansky. iscas 2010: 2015-2018 [doi]

Comparison of modulation features for phoneme recognitionSriram Ganapathy, Samuel Thomas, Hynek Hermansky. icassp 2010: 5038-5041 [doi]

Autoregressive Models of Amplitude Modulations in Audio CompressionSriram Ganapathy, Petr Motlícek, Hynek Hermansky. taslp, 18(6):1624-1631, 2010. [doi]

Robust spectro-temporal features based on autoregressive models of Hilbert envelopesSriram Ganapathy, Samuel Thomas, Hynek Hermansky. icassp 2010: 4286-4289 [doi]

History of modulation spectrum in ASRHynek Hermansky. icassp 2010: 5458-5461 [doi]

Towards spoken term discovery at scale with zero resourcesAren Jansen, Kenneth Church, Hynek Hermansky. interspeech 2010: 1676-1679 [doi]

Recovery of Rare Words in Lecture SpeechStefan Kombrink, Mirko Hannemann, Lukas Burget, Hynek Hermansky. TSD 2010: 330-337 [doi]

The use of spike-based representations for hardware audition systemsShih-Chii Liu, Nima Mesgarani, John G. Harris, Hynek Hermansky. iscas 2010: 505-508 [doi]

A multistream multiresolution framework for phoneme recognitionNima Mesgarani, Samuel Thomas, Hynek Hermansky. interspeech 2010: 318-321 [doi]

Wide-Band Audio Coding Based on Frequency-Domain Linear PredictionPetr Motlícek, Sriram Ganapathy, Hynek Hermansky, Harinath Garudadri. ejasmp, 2010, 2010. [doi]

Sparse coding for speech recognitionGarimella S. V. S. Sivaram, Sridhar Krishna Nemala, Mounya Elhilali, Trac D. Tran, Hynek Hermansky. icassp 2010: 4346-4349 [doi]

Sparse auto-associative neural networks: theory and application to speech recognitionGarimella S. V. S. Sivaram, Sriram Ganapathy, Hynek Hermansky. interspeech 2010: 2270-2273 [doi]

Cross-lingual and multi-stream posterior features for low resource LVCSR systemsSamuel Thomas, Sriram Ganapathy, Hynek Hermansky. interspeech 2010: 877-880 [doi]

A phoneme recognition framework based on auditory spectro-temporal receptive fieldsSamuel Thomas, Kailash Patil, Sriram Ganapathy, Nima Mesgarani, Hynek Hermansky. interspeech 2010: 2458-2461 [doi]

2009

Error Resilient Speech Coding Using Sub-band Hilbert EnvelopesSriram Ganapathy, Petr MotlÃcek, Hynek Hermansky. TSD 2009: 355-362 [doi]

Static and dynamic modulation spectrum for speech recognitionSriram Ganapathy, Samuel Thomas, Hynek Hermansky. interspeech 2009: 2823-2826 [doi]

Posterior-based out of vocabulary word detection in telephone speechStefan Kombrink, Lukás Burget, Pavel Matejka, Martin Karafiát, Hynek Hermansky. interspeech 2009: 80-83 [doi]

Discriminant spectrotemporal features for phoneme recognitionNima Mesgarani, Garimella S. V. S. Sivaram, Sridhar Krishna Nemala, Mounya Elhilali, Hynek Hermansky. interspeech 2009: 2983-2986 [doi]

Arithmetic coding of sub-band residuals in FDLP speech/audio codecPetr Motlícek, Sriram Ganapathy, Hynek Hermansky. interspeech 2009: 2591-2594 [doi]

Reconciliation of human and machine speech recognition performanceMisha Pavel, Malcolm Slaney, Hynek Hermansky. icassp 2009: 1669-1672 [doi]

Volterra series for analyzing MLP based phoneme posterior estimatorJoel Pinto, Garimella S. V. S. Sivaram, Hynek Hermansky, Mathew Magimai-Doss. icassp 2009: 1813-1816 [doi]

Intelligent Multi-modal Interfaces for Mobile Applications in Hostile Environment(IM-HOST)Claude Stricker, Jean-FrÃ©dÃ©ric Wagen, Guillermo Aradilla, HervÃ© Bourlard, Hynek Hermansky, Joel Pinto, Paul-Henri Rey, JÃ©rÃ´me ThÃ©raulaz. In Denis Lalanne, JÃ¼rg Kohlas, editors, Human Machine Interaction, Research Results of the MMI Program. Volume 5440 of Lecture Notes in Computer Science, pages 71-102, Springer, 2009. [doi]

Phoneme recognition using spectral envelope and modulation frequency featuresSamuel Thomas, Sriram Ganapathy, Hynek Hermansky. icassp 2009: 4453-4456 [doi]

Tandem representations of spectral envelope and modulation frequency features for ASRSamuel Thomas, Sriram Ganapathy, Hynek Hermansky. interspeech 2009: 2955-2958 [doi]

2008

The DIRAC AWEAR audio-visual platform for detection of unexpected and incongruent eventsJörn Anemüller, Jörg-Hendrik Bach, Barbara Caputo, Michal Havlena, Jie Luo, Hendrik Kayser, Bastian Leibe, Petr Motlícek, Tomás Pajdla, Misha Pavel, Akihiko Torii, Luc J. Van Gool, Alon Zweig, Hynek Hermansky. icmi 2008: 289-292 [doi]

Combination of strongly and weakly constrained recognizers for reliable detection of OOVSLukas Burget, Petr Schwarz, Pavel Matejka, Mirko Hannemann, Ariya Rastrow, Christopher White, Sanjeev Khudanpur, Hynek Hermansky, Jan CernockÃ½. icassp 2008: 4081-4084 [doi]

Front-end for far-field speech recognition based on frequency domain linear predictionSriram Ganapathy, Samuel Thomas, Hynek Hermansky. interspeech 2008: 984-987 [doi]

Spectral noise shaping: improvements in speech/audio codec based on linear prediction in spectral domainSriram Ganapathy, Petr Motlícek, Hynek Hermansky, Harinath Garudadri. interspeech 2008: 675-678 [doi]

Temporal masking for bit-rate reduction in audio codec based on Frequency Domain Linear PredictionSriram Ganapathy, Petr MotlÃcek, Hynek Hermansky, Harinath Garudadri. icassp 2008: 4781-4784 [doi]

Perceptually Motivated Sub-band Decomposition for FDLP Audio CodingPetr Motlícek, Sriram Ganapathy, Hynek Hermansky, Harinath Garudadri, Marios Athineos. TSD 2008: 435-442 [doi]

Exploiting Contextual Information for Speech/Non-Speech DetectionSree Hari Krishnan Parthasarathi, Petr Motlícek, Hynek Hermansky. TSD 2008: 451-459 [doi]

Reverse Correlation for Analyzing MLP Posterior Features in ASRJoel Pinto, Garimella S. V. S. Sivaram, Hynek Hermansky. TSD 2008: 469-476 [doi]

Exploiting contextual information for improved phoneme recognitionJoel Pinto, B. Yegnanarayana, Hynek Hermansky, Mathew Magimai-Doss. icassp 2008: 4449-4452 [doi]

Combining evidence from a generative and a discriminative model in phoneme recognitionJoel Pinto, Hynek Hermansky. interspeech 2008: 2414-2417 [doi]

Emulating Temporal Receptive Fields of Higher Level Auditory Neurons for ASRGarimella S. V. S. Sivaram, Hynek Hermansky. TSD 2008: 509-516 [doi]

Introducing temporal asymmetries in feature extraction for automatic speech recognitionGarimella S. V. S. Sivaram, Hynek Hermansky. interspeech 2008: 890-893 [doi]

Hilbert envelope based spectro-temporal features for phoneme recognition in telephone speechSamuel Thomas, Sriram Ganapathy, Hynek Hermansky. interspeech 2008: 1521-1524 [doi]

Hilbert Envelope Based Features for Far-Field Speech RecognitionSamuel Thomas, Sriram Ganapathy, Hynek Hermansky. mlmi 2008: 119-124 [doi]

Hierarchical and parallel processing of modulation spectrum for ASR applicationsFabio Valente, Hynek Hermansky. icassp 2008: 4165-4168 [doi]

On the combination of auditory and modulation frequency channels for ASR applicationsFabio Valente, Hynek Hermansky. interspeech 2008: 2242-2245 [doi]

Beyond Novelty Detection: Incongruent Events, when General and Specific Classifiers DisagreeDaphna Weinshall, Hynek Hermansky, Alon Zweig, Jie Luo, Holly Brügge Jimison, Frank Ohl, Misha Pavel. nips 2009: 1745-1752 [doi]

Confidence estimation, OOV detection and language ID using phone-to-word transduction and phone-level alignmentsChristopher White, Geoffrey Zweig, Lukas Burget, Petr Schwarz, Hynek Hermansky. icassp 2008: 4085-4088 [doi]

2007

Detection of out-of-vocabulary words in posterior based ASRHamed Ketabdar, Mirko Hannemann, Hynek Hermansky. interspeech 2007: 1757-1760 [doi]

Frequency Domain Linear Prediction for QMF Sub-bands and Applications to Audio CodingPetr Motlícek, Sriram Ganapathy, Hynek Hermansky, Harinath Garudadri. mlmi 2008: 248-258 [doi]

Non-uniform Speech/Audio Coding Exploiting Predictability of Temporal Evolution of Spectral EnvelopesPetr Motlícek, Hynek Hermansky, Sriram Ganapathy, Harinath Garudadri. TSD 2007: 350-357 [doi]

Wide-Band Perceptual Audio Coding Based on Frequency-Domain Linear PredictionPetr Motlícek, Vijay Ullal, Hynek Hermansky. icassp 2007: 265-268 [doi]

Exploiting phoneme similarities in hybrid HMM-ANN keyword spottingJoel Pinto, Andrew Lovitt, Hynek Hermansky. interspeech 2007: 1817-1820 [doi]

MRASTA and PLP in automatic speech recognitionS. R. Mahadeva Prasanna, Hynek Hermansky. interspeech 2007: 1166-1169 [doi]

Hierarchical neural networks feature extraction for LVCSR systemFabio Valente, Jithendra Vepa, Christian Plahl, Christian Gollan, Hynek Hermansky, Ralf Schlüter. interspeech 2007: 42-45 [doi]

Multi-stream features combination based on dempster-shafer rule for LVCSR systemFabio Valente, Jithendra Vepa, Hynek Hermansky. interspeech 2007: 1154-1157 [doi]

2006

Speech Coding Based on Spectral DynamicsPetr Motlícek, Hynek Hermansky, Harinath Garudadri, Naveen Srinivasamurthy. TSD 2006: 471-478 [doi]

Discriminant linear processing of time-frequency planeFabio Valente, Hynek Hermansky. interspeech 2006: [doi]

2005

The Role of Speech in Multimodal Human-Computer InteractionHynek Hermansky, Petr Fousek, Mikko Lehtonen. TSD 2005: 2-8 [doi]

Multi-resolution RASTA filtering for TANDEM-based ASRHynek Hermansky, Petr Fousek. interspeech 2005: 361-364 [doi]

EditorialWerner Verhelst, Jürgen Herre, Gernot Kubin, Hynek Hermansky, Søren Holdt Jensen. ejasp, 2005(9):1289-1291, 2005. [doi]

2004

2003

Segmentation of speech for speaker and language recognitionAndré Gustavo Adami, Hynek Hermansky. interspeech 2003: [doi]

Local averaging and differentiating of spectral plane for TRAP-based ASRFrantisek Grézl, Hynek Hermansky. interspeech 2003: [doi]

Band-independent speech-event categories for TRAP based ASRHynek Hermansky, Pratibha Jain. interspeech 2003: [doi]

Beyond a single critical-band in TRAP based ASRPratibha Jain, Hynek Hermansky. interspeech 2003: [doi]

Novel approaches for one- and two-speaker detectionSachin S. Kajarekar, André Gustavo Adami, Hynek Hermansky. interspeech 2003: [doi]

Data-driven spectral basis functions for automatic speech recognitionNaren Malayath, Hynek Hermansky. speech, 40(4):449-466, 2003. [doi]

Phoneme Recognition Using Temporal PatternsPavel Matejka, Petr Schwarz, Hynek Hermansky, Jan Cernocký. TSD 2003: 198-205 [doi]

In search of target class definition in tandem feature extractionSunil Sivadas, Hynek Hermansky. interspeech 2003: [doi]

2002

2001

2000

Temporal patterns of critical-band spectrum for text-to-speechPratibha Jain, Hynek Hermansky. interspeech 2000: 439-441 [doi]

Optimization of units for continuous-digit recognition taskSachin S. Kajarekar, Hynek Hermansky. interspeech 2000: 539-542 [doi]

Analysis of Information in Speech and Its Application in Speech RecognitionSachin S. Kajarekar, Hynek Hermansky. TSD 2000: 283-288 [doi]

Data-Driven Temporal Filters and Alternatives to GMM in Speaker VerificationNaren Malayath, Hynek Hermansky, Sachin S. Kajarekar, B. Yegnanarayana. dsp, 10(1-3):55-74, 2000. [doi]

Discriminative MLPs in HMM-based recognition of speech in cellular telephonySunil Sivadas, Pratibha Jain, Hynek Hermansky. interspeech 2000: 153-156 [doi]

Relevance of time-frequency features for phonetic and speaker-channel classificationHoward Hua Yang, Sarel Van Vuuren, Sangita Sharma, Hynek Hermansky. speech, 31(1):35-50, 2000. [doi]

1999

Down-sampling speech representation in ASRHynek Hermansky, Pratibha Jain. interspeech 1999: [doi]

Data-Driven Analysis of SpeechHynek Hermansky. TSD 1999: 10-18 [doi]

Analysis of sources of variability in speechSachin S. Kajarekar, Narendranath Malayath, Hynek Hermansky. interspeech 1999: [doi]

On the relative importance of various components of the modulation spectrum for automatic speech recognitionNoboru Kanedera, Takayuki Arai, Hynek Hermansky, Misha Pavel. speech, 28(1):43-55, 1999. [doi]

Speech variability in the modulation spectral domain - SANOVA technique -Sarel Van Vuuren, Hynek Hermansky. interspeech 1999: [doi]

Search for Information Bearing Components in SpeechHoward Hua Yang, Hynek Hermansky. nips 2000: 803-812 [doi]

Speech enhancement using linear prediction residualB. Yegnanarayana, Carlos Avendaño, Hynek Hermansky, P. Satyanarayana Murthy. speech, 28(1):25-42, 1999. [doi]

1998

Should recognizers have ears?Hynek Hermansky. speech, 25(1-3):3-27, 1998. [doi]

TRAPS - classifiers of temporal patternsHynek Hermansky, Sangita Sharma. interspeech 1998: [doi]

Spectral basis functions from discriminant analysisHynek Hermansky, Narendranath Malayath. interspeech 1998: [doi]

On the importance of components of the modulation spectrum for speaker verificationSarel Van Vuuren, Hynek Hermansky. interspeech 1998: [doi]

1997

PreviousNext