Keywords:
- Acoustic model adaptation
- acoustic modeling
- Afrikaans
- audiobook
- Automatic Speech Recognition
- Deep learning for speech
- deep MLPs
- deep neural networks
- dnn
- exemplar-based modeling
- fast adaptation
- fast training
- fmllr
- Gaussian Mixture Models
- Hidden Markov Model
- hidden variable
- hybrid system
- KL-HMM
- Kullback-Leibler divergence
- lan- guage identification
- multilayer perceptron
- multilingual acoustic modeling
- Multilingual automatic speech recognition
- multilingual speech recognition
- neural network
- neural network features
- non-native speech
- parametric synthesis
- posterior feature
- Posterior features
- Prosodic features
- Semi-supervised training
- sparse representation
- speaker adaptation
- Speaker Diarization
- speech recognition
- speech synthesis
- Subs-ace Gaussian Mixture Models
- Tandem
- text to speech
- text-to-speech
- text-to-speech synthesis
- triphone mapping
- under-resourced languages
- under-resourced speech recognition
- universal phoneme set
Publications of David Imseng sorted by recency
| 1 | 2 |
| Comparative Study on Sentence Boundary Prediction for German and English Broadcast News, , , , and , Idiap-RR-18-2017 |
|
| Feature mapping using far-field microphones for distant speech recognition, , , and , Idiap-RR-20-2016 |
|
| Feature mapping using far-field microphones for distant speech recognition, , , and , in: Speech Communication, 83:1-9, 2016 |
[DOI] [URL] |
| Exploiting foreign resources for DNN-based ASR, , , , and , in: EURASIP Journal on Audio, Speech, and Music Processing(2015:17), 2015 |
[DOI] |
| Exploiting foreign resources for DNN-based ASR, , , , and , Idiap-RR-27-2015 |
|
| Learning Feature Mapping using Deep Neural Network Bottleneck Features for Distant Large Vocabulary Speech Recognition, , , , , and , in: IEEE International Conference on Acoustics, Speech, and Signal Processing, pages 4540-4544, 2015 |
[DOI] |
| Building context-dependent DNN acoustic models using Kullback-Leibler divergence-based state tying, , , and , in: Proceedings IEEE International Conference on Acoustics, Speech and Signal Processing, 2015 |
|
| Preliminary Work on Speaker Adaptation for DNN-Based Speech Synthesis, , and , Idiap-RR-02-2015 |
|
| Development of Bilingual ASR System for MediaParl Corpus, , , and , in: Proceedings of the 15th Annual Conference of the International Speech Communication Association (Interspeech 2014), Singapore, ISCA, 2014 |
|
| Development of Bilingual ASR System for MediaParl Corpus, , , and , Idiap-RR-21-2014 |
|
| Automatic Speech Recognition and Translation of a Swiss German Dialect: Walliserdeutsch, , and , in: Proceedings of Interspeech, 2014 |
|
| Posterior-based Sparse Representation for Automatic Speech Recognition, , , and , in: Proceeding of Interspeech, 2014 |
|
| Improving Real Time Factor of Information Bottleneck-based Speaker Diarization System, , and , Idiap-RR-18-2015 |
|
| Multilingual Deep Neural Network based Acoustic Modeling For Rapid Language Adaptation, , , , , and , in: Proceedings IEEE International Conference on Acoustics, Speech and Signal Processing, Florence, pages 7639-7643, IEEE, 2014 |
[DOI] |
| Exploiting un-transcribed foreign data for speech recognition in well-resourced languages, , , , and , in: Proceedings IEEE International Conference on Acoustics, Speech and Signal Processing, Florence, IT, pages 2322 - 2326, IEEE, 2014 |
[DOI] |
| Crosslingual Tandem-SGMM: Exploiting Out-Of-Language Data for Acoustic Model and Feature Level Adaptation, , and , in: Proceedings of the 14th Annual Conference of the International Speech Communication Association (Interspeech 2013), ISCA - International Speech Communication Association, Lyon, France, pages 510-514, ISCA, 2013 |
|
| Crosslingual Tandem-SGMM: Exploiting Out-Of-Language Data for Acoustic Model and Feature Level Adaptation, , and , Idiap-RR-39-2013 |
|
| Impact of deep MLP architecture on different acoustic modeling techniques for under-resourced speech recognition, , , and , in: Proceedings of the IEEE workshop on Automatic Speech Recognition and Understanding, 2013 |
|
| Multilingual speech recognition A posterior based approach, , École Polytechnique Fédérale de Lausanne (EPFL), 2013 |
|
| Applying multi- and cross-lingual stochastic phone space transformations to non-native speech recognition, , , , and , in: IEEE Transactions on Audio, Speech, and Language Processing, 2013 |
[DOI] |
| Statistical models for HMM/ANN hybrids, and , Idiap-RR-11-2013 |
|
| Speaker adaptive Kullback-Leibler divergence based hidden Markov models, and , in: Proceedings IEEE International Conference on Acoustics, Speech and Signal Processing, 2013 |
|
| Using out-of-language data to improve an under-resourced speech recognizer, , , and , Idiap-RR-09-2013 |
|
| Using out-of-language data to improve an under-resourced speech recognizer, , , and , in: Speech Communication, 2013 |
[DOI] [URL] |
| Leveraging speaker diarization for meeting recognition from distant microphones, , and , in: Proceedings IEEE International Conference on Acoustics, Speech and Signal Processing, pages 4390--4393, 2010 |
| MediaParl: Bilingual mixed language accented speech database, , , , , and , Idiap-RR-03-2013 |
|
| MediaParl: Bilingual mixed language accented speech database, , , , , and , in: Proceedings of the 2012 IEEE Workshop on Spoken Language Technology, pages 263--268, 2012 |
|
| Application of Subspace Gaussian Mixture Models in Contrastive Acoustic Scenarios, , , and , Idiap-RR-20-2012 |
|
| Robust triphone mapping for acoustic modeling, , and , Idiap-RR-02-2013 |
|
| Robust triphone mapping for acoustic modeling, , and , in: Proceedings of Interspeech, Portland, Oregon, 2012 |
|
| Comparing different acoustic modeling techniques for multilingual boosting, , , , and , Idiap-RR-01-2013 |
|
| Comparing different acoustic modeling techniques for multilingual boosting, , , , and , in: Proceedings of Interspeech, Portland, Oregon, 2012 |
|
| Boosting under-resourced speech recognizers by exploiting out of language data - Case study on Afrikaans, , and , Idiap-RR-15-2012 |
|
| Boosting under-resourced speech recognizers by exploiting out of language data - Case study on Afrikaans, , and , in: Proceedings of the 3rd International Workshop on Spoken Languages Technologies for Under-resourced Languages, Cape Town, pages 60--67, 2012 |
|
| Decision tree clustering for KL-HMM, and , Idiap-Com-01-2012 |
|
| The ICSI RT-09 Speaker Diarization System, , , , , , , and , in: IEEE Transactions on Audio, Speech, and Language Processing, 20(2):371--381, 2012 |
[DOI] |
| Using KL-divergence and multilingual information to improve ASR for under-resourced languages, , and , in: Proceedings IEEE International Conference on Acoustics, Speech and Signal Processing, Kyoto, pages 4869--4872, 2012 |
|
| Current trends in multilingual speech processing, , , , , , , , and , in: Sadhana, 36(5):885–915, 2011 |
[DOI] [URL] |
| 1 | 2 |