Desh Raj

8 papers · 2017–2024 · 3 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 ↓

+2 more ↓

🌉 Interdisciplinary Bridge · Silver 🏃 Academic Marathon · Sprint 🗺️ Taxonomy Completionist (19) 🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Bronze

🧭 Keyword Pioneer 🌈 Renaissance Researcher (5)

Venues

Interspeech (6) COLING (1) CoNLL (1)

Top co-authors

Sanjeev Khudanpur (5) Jan Trmal (2) Shinji Watanabe (2) Ruizhe Huang (2) Daniel Povey (2) Matthew Wiesner (2) Dongji Gao (1) Ariya Rastrow (1) Zhuo Chen (1) Maokui He (1)

Research topics

Machine Learning (6) Speech & Audio (6) Core Methods (4) Recognition (4) Artificial Intelligence (2) Deep Learning (2) Analysis (2) Application Areas (2) Synthesis (2) Computer Science (1) Mathematics & Optimization (1) Natural Language Processing (1) Applications (1) Architectures (1) Core AI (1)

Keywords

speaker diarization (2) speech recognition (1) attentive pooling (1) language identification (1) weak supervision (1) speech enhancement (1) acoustic modeling (1) graph partitioning (1) speaker attribution (1) approximation algorithm (1) gpu acceleration (1) biomedical text (1) earnings call (1) relation classification (1) automatic speech recognition (1) code-switched speech recognition (1) neural transducer (1) word error rate (1) multi-task learning (1) combinatorial optimization (1)

Papers

ConEC: Earnings Call Dataset with Real-world Contexts for Benchmarking Contextual Speech Recognition COLING 2024 Enhancing Neural Transducer for Multilingual ASR with Synchronized Language Diarization Interspeech 2024 GPU-accelerated Guided Source Separation for Meeting Transcription Interspeech 2023 Auxiliary Loss Function for Target Speech Extraction and Recognition with Weak Supervision Based on Speaker Characteristics Interspeech 2021 Reformulating DOVER-Lap Label Mapping as a Graph Partitioning Problem Interspeech 2021 Target-Speaker Voice Activity Detection with Improved i-Vector Estimation for Unknown Number of Speaker Interspeech 2021 Training Hybrid Models on Noisy Transliterated Transcripts for Code-Switched Speech Recognition Interspeech 2021 Learning local and global contexts using a convolutional recurrent network model for relation classification in biomedical text CoNLL 2017