Keywords:
- acoustic modeling
- Alzheimer's disease
- articulatory features
- Automatic speaker verification (ASV)
- bag of audio words
- Children speech recognition
- confidence measures
- Convolution Neural Network
- Convolutional Neural Networks
- depression detection
- embedding
- end-to-end acoustic modeling
- end-to-end modelling
- end-to-end training
- expected performance and spoofability curve
- F1 score
- glottal source signals.
- integration of ASV and anti-spoofing
- local posterior probability
- low level descriptors
- Mental Lexicon
- Multi-modal Approach
- multitask learning
- Paralinguistic speech processing
- Perceived fluency
- Raw Speech
- raw waveform modelling
- segment-level training.
- sleepiness
- Speaker change detection
- speaker turn detection
- speech assessment
- Speech Emotion Recognition
- speech recognition
- spoofing detection
- Zero frequency filtering
- zero-frequency filtering
Publications of S. Pavankumar Dubagunta
2024
| Multitask Speech Recognition and Speaker Change Detection for Unknown Number of Speakers, , , , , , , and , in: Proceedings of the 49th IEEE International Conference on Acoustics, Speech, & Signal Processing (ICASSP) 2024, 2024 |
2023
| Towards learning emotion information from short segments of speech, , , , and , in: International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Rhodes Island, Greece, IEEE, 2023 |
|
2022
| Adjustable Deterministic Pseudonymization of Speech, , and , in: Computer, Speech & Language, 72, 2022 |
[DOI] |
| Towards Automatic Prediction of Non-Expert Perceived Speech Fluency Ratings, , , and , in: ACM International Conference on Multimodal Interaction (ICMI Companion), 2022 |
[DOI] |
2021
| Adjustable Deterministic Pseudonymization of Speech, , and , Idiap-RR-12-2021 |
|
| Late Fusion of the Available Lexicon and Raw Waveform-based Acoustic Modeling for Depression and Dementia Recognition, , , , , and , Idiap-RR-09-2021 |
|
| Late Fusion of the Available Lexicon and Raw Waveform-based Acoustic Modeling for Depression and Dementia Recognition, , , , , and , in: Proceedings of Interspeech 2021, ISCA-International Speech Communication Association 2021, 2021 |
|
| Novel Methods for Incorporating Prior Knowledge for Automatic Speech Assessment, , École polytechnique fédérale de Lausanne (EPFL), 2021 |
|
| On Joint Optimization of Automatic Speaker Verification and Anti-spoofing in the Embedding Space, , , , and , in: IEEE Transactions on Information Forensics and Security, 16:1579--1593, 2021 |
[DOI] |
| Towards Automatic Prediction of Non-Expert Perceived Speech Fluency Ratings, , , and , Idiap-RR-11-2021 |
|
2020
| Estimating The Degree of Sleepiness by Integrating Articulatory Feature Knowledge In Raw Waveform Based CNNs, , and , in: International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Barcelona, Spain, 2020 |
|
2019
| Estimating The Degree of Sleepiness by Integrating Articulatory Feature Knowledge In Raw Waveform Based CNNs, , and , Idiap-RR-06-2020 |
|
| Improving Children Speech Recognition through Feature Learning from Raw Speech Signal, , and , in: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2019 |
|
| Learning voice source related information for depression detection, , and , in: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2019 |
|
| Segment-level training of ANNs based on acoustic confidence measures for hybrid HMM/ANN Speech Recognition, and , in: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2019 |
|
| Understanding Raw Waveform based CNN through Low-rank Spectro-Temporal Decoupling, , and , Idiap-RR-11-2019 |
|
| Using Speech Production Knowledge for Raw Waveform Modelling based Styrian Dialect Identification, and , in: Proceedings of Interspeech, 2019 |
|