Leda Sarı

Publications by Year

Research Areas

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

Most-Cited Works

• → Ego4D: Around the World in 3,000 Hours of Egocentric Video(2022)487 cited
• → Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale(2023)45 cited
• → A Multi-View Approach to Audio-Visual Speaker Verification(2021)40 cited
• → Theoretical study of hydrogen abstraction from dimethyl ether and methyl tert-butyl ether by hydroxyl radicalElectronic supplementary information (ESI) available: optimized structural parameters, energies, zero point energies and dipole moments for reactants, products, and transition states (Tables S1–8). See http://www.rsc.org/suppdata/cp/b1/b109970c/(2002)29 cited
• → Unsupervised Speaker Adaptation Using Attention-Based Speaker Memory for End-to-End ASR(2020)24 cited
• → Towards Measuring Fairness in Speech Recognition: Casual Conversations Dataset Transcriptions(2022)18 cited
• → Self-Supervised Representations for Singing Voice Conversion(2023)16 cited
• → Pre-training of Speaker Embeddings for Low-latency Speaker Change Detection in Broadcast News(2019)15 cited
• → Training Spoken Language Understanding Systems with Non-Parallel Speech and Text(2020)15 cited
• → Fusion of LVCSR and posteriorgram based keyword search(2015)13 cited