164 results on '"Raj, Bhiksha"'
Search Results
2. Training Audio Captioning Models without Audio
3. uSee: Unified Speech Enhancement And Editing with Conditional Diffusion Models
4. Importance of Negative Sampling in Weak Label Learning
5. AugSumm: Towards Generalizable Speech Summarization Using Synthetic Labels from Large Language Models
6. Improving Continual Learning of Acoustic Scene Classification via Mutual Information Optimization
7. Fixed Inter-Neuron Covariability Induces Adversarial Robustness
8. Espnet-Summ: Introducing a Novel Large Dataset, Toolkit, and a Cross-Corpora Evaluation of Speech Summarization Systems
9. TAPLoss: A Temporal Acoustic Parameter Loss for Speech Enhancement
10. An Approach to Ontological Learning from Weak Labels
11. Privacy-Preserving Automatic Speaker Diarization
12. Paaploss: A Phonetic-Aligned Acoustic Parameter Loss for Speech Enhancement
13. FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understanding
14. Cross-utterance context for multimodal video transcription
15. The Right to Talk: An Audio-Visual Transformer Approach
16. Identifying Actions for Sound Event Classification
17. Self-Supervised 3D Face Reconstruction via Conditional Estimation
18. Contrast and Order Representations for Video Self-supervised Learning
19. FoolHD: Fooling Speaker Identification by Highly Imperceptible Adversarial Disturbances
20. The in-the-Wild Speech Medical Corpus
21. Towards Adversarial Robustness Via Compact Feature Representations
22. Contrast and Order Representations for Video Self-Supervised Learning
23. Detection and Evaluation of Human and Machine Generated Speech in Spoofing Attacks on Automatic Speaker Verification Systems
24. Hierarchical Routing Mixture of Experts
25. Exploiting Non-Linear Redundancy for Neural Model Compression
26. Optimal Strategies For Comparing Covariates To Solve Matching Problems
27. Sherlock: A Crowd-sourced System For Automatic Tagging Of Indoor Floor Plans
28. Deriving Compact Feature Representations Via Annealed Contraction
29. Optimizing Neural Network Embeddings Using a Pair-Wise Loss for Text-Independent Speaker Verification
30. In-the-Wild End-to-End Detection of Speech Affecting Diseases
31. Neural Regression Trees
32. Time Signal Classification Using Random Convolutional Features
33. Cross Modal Audio Search and Retrieval with Joint Embeddings Based on Text and Audio
34. Human Behaviour Recognition Using Wifi Channel State Information
35. Interactive Evaluation of Classifiers Under Limited Resources
36. Querying Depression Vlogs
37. Acoustic Scene Classification Using Discrete Random Hashing for Laplacian Kernel Machines
38. Framework for Evaluation of Sound Event Detection in Web Videos
39. Content-Based Representations of Audio Using Siamese Neural Networks
40. Voice Impersonation Using Generative Adversarial Networks
41. A Corrective Learning Approach for Text-Independent Speaker Verification
42. A two factor transformation for speaker verification through ℓ1 comparison
43. Inferring room semantics using acoustic monitoring
44. An approach for self-training audio event detectors using web data
45. SphereFace: Deep Hypersphere Embedding for Face Recognition
46. Audio event and scene recognition: A unified approach using strongly and weakly labeled data
47. Privacy preserving Distance computation using somewhat-trusted third parties
48. Supervised monaural source separation based on autoencoders
49. Discovering sound concepts and acoustic relations in text
50. Adaptation of SVM for MIL for inferring the polarity of movies and movie reviews
Catalog
Books, media, physical & digital resources
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.