Jisi Zhang

5 papers · 2021–2025 · 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 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (16) 🐣 Hot Topic Early Bird 🔥 Unstoppable · Bronze

Venues

Interspeech (4) EMNLP (1)

Top co-authors

Karthikeyan Saravanan (3) Pablo Peso Parada (3) Cătălin Zorilă (2) Jon Barker (2) Anastasios Drosou (2) Md Asif Jalal (2) Rama Doddipatla (2) Jung In Lee (1) Konstantinos Nikiforidis (1) Myoungji Han (1)

Research topics

Machine Learning (5) Artificial Intelligence (3) Speech & Audio (3) Learning Types (3) Recognition (3) Deep Learning (2) Application Areas (2) Core AI (2) Natural Language Processing (1) Security & Privacy (1) Analysis (1) Applications (1) Architectures (1) Generation (1) Learning Paradigms (1)

Keywords

mixture invariant training (2) word error rate (2) automatic speech recognition (2) speech separation (2) privacy preservation (1) speech enhancement (1) speaker recognition (1) parameter efficiency (1) retrieval-augmented generation (1) teacher-student training (1) context-aware system (1) robust speech recognition (1) noisy speech (1) permutation invariant training (1) out-of-vocabulary term (1) acoustic embedding (1) gradient reversal layer (1) speaker anonymization (1) text-to-music generation (1) gradient reversal (1)

Papers

Retrieval Augmented Generation based context discovery for ASR EMNLP 2025 Exploring compressibility of transformer based text-to-music (TTM) models Interspeech 2024 On-Device Speaker Anonymization of Acoustic Embeddings for ASR based on Flexible Location Gradient Reversal Layer Interspeech 2023 On monoaural speech enhancement for automatic recognition of real noisy speech using mixture invariant training Interspeech 2022 Teacher-Student MixIT for Unsupervised and Semi-Supervised Speech Separation Interspeech 2021