Sarthak Yadav

5 papers · 2018–2025 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (14)

Venues

Interspeech (4) ICLR (1)

Top co-authors

Zheng-Hua Tan (3) Sergios Theodoridis (2) Neil Zeghidour (1) Lars Kai Hansen (1) Atul Rai (1)

Research topics

Deep Learning (5) Architectures (5) Machine Learning (4) Speech & Audio (4) Learning Types · Machine Learning (4) Learning Types · Deep Learning (3) Analysis (2) Core Methods (2) Models (2) Processing (1) Recognition (1)

Keywords

self-supervised learning (4) feature learning (2) audio representation (2) speaker verification (1) speaker recognition (1) audio classification (1) state space model (1) convolutional neural network (1) pre-trained model (1) masked autoencoder (1) discriminative feature (1) multi-head attention (1) speaker identification (1) mel filterbank (1) local-global attention (1) self-supervised audio representation (1) audio recognition (1) center loss (1) discriminative feature learning (1) text-independent recognition (1)

Papers

AxLSTMs: learning self-supervised audio representations with xLSTMs Interspeech 2025 Audio Mamba: Selective State Spaces for Self-Supervised Audio Representations Interspeech 2024 Masked Autoencoders with Multi-Window Local-Global Attention Are Better Audio Learners ICLR 2024 Learning neural audio features without supervision Interspeech 2022 Learning Discriminative Features for Speaker Identification and Verification Interspeech 2018