Keywords:
- Automatic Speech Recognition
- automatic subword unit derivation
- Conditional Random Fields
- grapheme subwords
- grapheme-to- phoneme conversion
- grapheme-to-phoneme conversion
- Graphemes
- Hidden Markov Model
- Kullback-Leibler divergence based hidden Markov model
- Kullback-Leibler divergence based HMM
- multi-stream combination
- phoneme subwords
- phonemes
- probabilistic lexical modeling
- pronunciation generation
- pronunciation lexicon
- under-resourced languages
- unsupervised adaptation
- zero-resourced speech recognition
Publications of Marzieh Razavi sorted by journal and type
Publications of type Idiap-RR
2019
| Data-Driven Movement Subunit Extraction from Skeleton Information for Modeling Signs and Gestures, , and , Idiap-RR-02-2019 |
|
| TOWARDS MULTILINGUAL SIGN LANGUAGE RECOGNITION, , and , Idiap-RR-16-2019 |
|
2017
| Towards Weakly Supervised Acoustic Subword Unit Discovery and Lexicon Development Using Hidden Markov Models, , and , Idiap-RR-15-2017 |
|
2015
| Acoustic Data-Driven Grapheme-to-Phoneme Conversion in the Probabilistic Lexical Modeling Framework, , and , Idiap-RR-10-2015 |
|
| On the Application of Automatic Subword Unit Derivation and Pronunciation Generation for Under-Resourced Language ASR: A Study on Scottish Gaelic, , and , Idiap-RR-13-2015 |
|
| Posterior-Based Multi-Stream Formulation To Combine Multiple Grapheme-to-Phoneme Conversion Techniques, and , Idiap-RR-33-2015 |
|
| Towards Multiple Pronunciation Generation in Acoustic G2P Conversion Framework, , and , Idiap-RR-34-2015 |
|
2013
| On Modeling Context-dependent Clustered States: Comparing HMM/GMM, Hybrid HMM/ANN and KL-HMM Approaches, , and , Idiap-RR-43-2013 |
|
IEEE Signal Processing Letters
| A Posterior-Based Multi-Stream Formulation for G2P Conversion, and , in: IEEE Signal Processing Letters, 2017 |
|
Speech Communication
| Towards Weakly Supervised Acoustic Subword Unit Discovery and Lexicon Development Using Hidden Markov Models, , and , in: Speech Communication, 96:168-183, 2018 |
[DOI] |
| Acoustic data-driven grapheme-to-phoneme conversion in the probabilistic lexical modeling framework, , and , in: Speech Communication, 80, 2016 |
[DOI] |
Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) (2020)
| Towards Multilingual Sign Language Recognition, , and , in: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2020 |
|
Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) (2019)
| HMM-based Approaches to Model Multichannel Information in Sign Language inspired from Articulatory Features-based Speech Processing, , , , and , in: Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2019 |
|
Language Resources and Evaluation Conference (2018)
| SMILE Swiss German Sign Language Dataset, , , , , , , , , , , and , in: Language Resources and Evaluation Conference, 2018 |
Proceedings of Interspeech (2016)
| Improving Under-Resourced Language ASR Through Latent Subword Unit Space Discovery, and , in: Proceedings of Interspeech, 2016 |
|
International Conference on Acoustics, Speech and Signal Processing (2015)
| An HMM-Based Formalism for Automatic Subword Unit Derivation and Pronunciation Generation, and , in: International Conference on Acoustics, Speech and Signal Processing, pages 4639-4643, IEEE, 2015 |
[DOI] |
| Integrated Pronunciation Learning for Automatic Speech Recognition Using Probabilistic Lexical Modeling, , and , in: International Conference on Acoustics, Speech and Signal Processing, South Brisbane, QLD, pages 5176-5180, 2015 |
[DOI] |
4th Biennial Workshop on Less-Resourced Languages (2015)
| Pronunciation Lexicon Development for Under-Resourced Languages Using Automatically Derived Subword Units: A Case Study on Scottish Gaelic, , and , in: 4th Biennial Workshop on Less-Resourced Languages, 2015 |
|
International Conference on Acoustics, Speech, and Signal Processing (2014)
| On Modeling Context-Dependent Clustered States: Comparing HMM/GMM, Hybrid HMM/ANN and KL-HMM Approaches, , and , in: International Conference on Acoustics, Speech, and Signal Processing, Florence, IT, pages 7659 - 7663, IEEE, 2014 |
[DOI] |
Proceedings of the 15th Annual Conference of the International Speech Communication Association (Interspeech 2014) (2014)
| On Recognition of Non-Native Speech Using Probabilistic Lexical Model, and , in: Proceedings of the 15th Annual Conference of the International Speech Communication Association (Interspeech 2014), 2014 |
|
Proceedings of the IEEE workshop on Automatic Speech Recognition and Understanding (2013)
| Probabilistic Lexical Modeling and Unsupervised Training for Zero-Resourced ASR, , and , in: Proceedings of the IEEE workshop on Automatic Speech Recognition and Understanding, 2013 |
|
Publications of type Phdthesis
2017
| On Modeling the Synergy Between Acoustic and Lexical Information for Pronunciation Lexicon Development, , École polytechnique fédérale de Lausanne (EPFL), 2017 |
[DOI] |