Keywords:
- adaptation
- ADS-B data
- Air traffic control
- air traffic control communications
- AM
- Anti-spoofing
- audio and voice analysis
- Automatic Speech Recognition
- automatic speech recognition (ASR)
- automatic speech recognition and understanding
- batch norm
- batch normalization
- bayesian fusion
- Call-sign Recognition
- Contextual Adaptation
- contextual biasing
- conversational modeling
- Convolutional Neural Networks
- Cross-modal Alignment
- Cross-modal Attentio
- Cross-modal Attention
- ctc
- Data Selection
- deep neural networks
- depression detection
- domain adaptation
- Domain Classification
- e2e-lfmmi
- entity linking
- F1 score
- fine-tuning
- finite-state transducers
- FM
- Forensics
- GPU decoding
- Graph Neural Networks
- Human-Computer Interaction
- i-vector
- i-vectors
- Intent Classification
- inter-task fusion
- Interpretability
- Interpretable Models
- knowledge distillation
- language identification
- Language Production
- LEA
- limited training data
- Linear prediction
- logistic regression
- low-resource
- Mental Lexicon
- multi-lingual automatic speech recognition
- multi-lingual SAD
- Multilingual automatic speech recognition
- multitask learning
- multitask training
- named entity recognition
- node weighted graphs
- online speech recognition
- OOV-word recognition
- OpenSky Network
- OSINT
- out-of-domain
- rare word recognition
- real-time speech recognition
- ROXANNE
- ROXSD
- sentence embeddings
- Speaker change detection
- speaker clustering
- Speaker identification
- speaker recognition
- speaker role detection
- speaker turn detection
- speaker verification
- Speech activity detection
- speech dataset
- speech recognition
- spoken dialogue systems
- Spoken Language Understanding
- subspace Gaussian mixture models
- supervised adaptation
- task-oriented dialog
- Text classification
- transfer learning
- transformers
- user identity linkage
- wav2vec 2.0
- wav2vec2
- whisper
- Word Consensus Networks
- Word-Confusion-Networks
- XLSR-Transducer
- Zipformer
Publications of Srikanth Madikeri
2020
| A BAYESIAN APPROACH TO INTER-TASK FUSION FOR SPEAKER RECOGNITION, , and , Idiap-RR-07-2020 |
|
| AM-FM DECOMPOSITION OF SPEECH SIGNAL: APPLICATIONS FOR SPEECH PRIVACY AND DIAGNOSIS, , , , and , Idiap-RR-01-2020 |
|
| INCREMENTAL SEMI-SUPERVISED LEARNING FOR MULTI-GENRE SPEECH RECOGNITION, , , , , and , in: Proceedings of ICASSP 2020, 2020 |
|
| Lattice-Free Maximum Mutual Information Training of Multilingual Speech Recognition System, , , , , and , Idiap-RR-28-2020 |
|
| Lattice-Free Maximum Mutual Information Training of Multilingual Speech Recognition System, , , , , and , in: In Proceedings of Interspeech 2020, pages 4746--4750, ISCA, 2020 |
|
| LATTICE-FREE MMI ADAPTATION OF SELF-SUPERVISED PRETRAINED ACOUSTIC MODELS, , and , Idiap-RR-40-2020 |
[URL] |
| Novel Architectures for Unsupervised Information Bottleneck based Speaker Diarization of Meetings, , , and , Idiap-RR-26-2020 |
|
| Novel Architectures for Unsupervised Information Bottleneck based Speaker Diarization of Meetings, , , and , in: IEEE/ACM Transactions on Audio Speech and Language Processing, 2020 |
| Supervised domain adaptation for text-independent speaker verification using limited data, , , and , in: Interspeech, pages 3815-3819, 2020 |
[URL] |
2019
| A BAYESIAN APPROACH TO INTER-TASK FUSION FOR SPEAKER RECOGNITION, , and , in: In Proceedings of ICASSP 2019, Brighton, ENGLAND, pages 5786-5790, 2019 |
|
| AM-FM DECOMPOSITION OF SPEECH SIGNAL: APPLICATIONS FOR SPEECH PRIVACY AND DIAGNOSIS, , , , and , in: 11th International workshop on Models and Analysis of Vocal Emissions for Biomedical Applications, Universita Degli Studi Firenze, Firenze, Italy, 2019 |
[URL] |
| Idiap submission to the NIST SRE 2018 Speaker Recognition Evaluation, , , and , Idiap-RR-17-2019 |
|
| Idiap submission to the NIST SRE 2019 Speaker Recognition Evaluation, , , , and , Idiap-RR-15-2019 |
|
| INCREMENTAL TRANSFER LEARNING IN TWO-PASS INFORMATION BOTTLENECK BASED SPEAKER DIARIZATION SYSTEM FOR MEETINGS, , , and , in: Proceedings of ICASSP 2019, pages 6291-6295, 2019 |
| INVESTIGATING TIME DELAY NEURAL NETWORK (TDNN) FOR LANGUAGE MODELING IN LOW RESOURCE AUTOMATIC SPEECH RECOGNITION, , , and , Idiap-RR-13-2019 |
|
| SARAL: A Low-Resource Cross-Lingual Domain-Focused Information Retrieval System for Effective Rapid Document Triage, , , , , , , , , , , and , in: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations. 2019, pages 19-24, 2019 |
| STACKED NEURAL NETWORKS WITH PARAMETER SHARING FOR MULTILINGUAL LANGUAGE MODELING, , , , , and , Idiap-RR-12-2019 |
|
| Voice Presentation Attack Detection Using Convolutional Neural Networks, , , , , and , in: Handbook of Biometric Anti-Spoofing, pages 391--415, Springer, 2019 |
[URL] |
2018
| Analysis of Language Dependent Front-End for Speaker Recognition, , and , in: Proceedings of Interspeech 2018, Hyderabad, INDIA, pages 1101-1105, 2018 |
[DOI] |
| Analysis of Posterior Estimation Approaches to I-vector Extraction for Speaker Recognition, , , and , Idiap-RR-15-2018 |
|
| DNN based speaker embedding using content information for text-dependent speaker verification, , , and , Idiap-RR-06-2018 |
|
| DNN based speaker embedding using content information for text-dependent speaker verification, , , and , in: Proceedings of 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2018 |
|
| End-to-end text-dependent speaker verification using novel distance measures, , and , in: Proceedings of Interspeech 2018, Hyderabad, INDIA, Aug 02-Sep 06, 2018, pages 3598-3602, 2018 |
[DOI] |
| SIIP: An Innovative Speaker Identification Approach for Law Enforcement Agencies, , , , , , , , , and , in: Big Data and Artificial Intelligence for Military Decision Making, http://www.sto.nato.int/, pages PT-1 - 1: PT-1 - 14, STO, 2018 |
[DOI] [URL] |
| Two-Pass IB based Speaker Diarization System using Meeting-Specific ANN based Features, , , and , Idiap-RR-09-2018 |
|
2017
| Content Normalization for Text-dependent Speaker Verification, , , and , in: Proc. of Interspeech, 2017 |
|
| CONTENT NORMALIZATION FOR TEXT-INDEPENDENT SPEAKER VERIFICATION, , , and , Idiap-RR-31-2017 |
|
| EXPLOITING SEQUENCE INFORMATION FOR TEXT-DEPENDENT SPEAKER VERIFICATION, , , and , Idiap-RR-04-2017 |
|
| EXPLOITING SEQUENCE INFORMATION FOR TEXT-DEPENDENT SPEAKER VERIFICATION, , , and , in: Proceedings of 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, New Orleans, pages 5370-5374, 2017 |
|
| INTRA-CLASS COVARIANCE ADAPTATION IN PLDA BACK-ENDS FOR SPEAKER VERIFICATION, , , and , Idiap-RR-05-2017 |
|
| INTRA-CLASS COVARIANCE ADAPTATION IN PLDA BACK-ENDS FOR SPEAKER VERIFICATION, , , and , in: Proceedings of International Conference on Acoustics, Speech and Signal Processing, pages 5365-5369, 2017 |
[DOI] |
| Template-matching for Text-dependent Speaker Verification, , , and , Idiap-RR-32-2017 |
|
| Template-matching for Text-dependent Speaker Verification, , , and , in: Speech Communication, 2017 |
|
| Towards a breakthrough speaker identification approach for law enforcement agencies, , , , , , , , , and , Idiap-RR-29-2017 |
|