Jay Mahadeokar

Publications by Year

Research Areas

Speech Recognition and Synthesis, Speech and Audio Processing, Natural Language Processing Techniques, Topic Modeling, Music and Audio Processing

Most-Cited Works

• → Transformer-Based Acoustic Modeling for Hybrid Speech Recognition(2020)254 cited
• → Prompting Large Language Models with Speech Recognition Abilities(2024)79 cited
• → Transformer-Transducer: End-to-End Speech Recognition with\n Self-Attention(2019)76 cited
• → Deep Shallow Fusion for RNN-T Personalization(2021)60 cited
• → Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion(2021)59 cited
• → Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale(2023)45 cited
• → RNN-T For Latency Controlled ASR With Improved Beam Search(2019)34 cited
• → Dissecting User-Perceived Latency of On-Device E2E Speech Recognition(2021)25 cited
• → Improved Neural Language Model Fusion for Streaming Recurrent Neural Network Transducer(2021)24 cited