Mike Seltzer

Computer Science · Physical Sciences

11h-index1.5kcitations40works7.92yr avg
OpenAlex↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Speech Recognition and Synthesis(31), Speech and Audio Processing(17), Natural Language Processing Techniques(13), Topic Modeling(10), Music and Audio Processing(10)

Publications40 total

Can Speech LLMs Think while Listening?
arXiv (Cornell University)·2025Open Access
SemAlignVC: Enhancing zero-shot timbre conversion using semantic alignment
arXiv (Cornell University)·2025Open Access
Get Large Language Models Ready to Speak: A Late-fusion Approach for Speech Generation
2025· 1 cited
Transducer-Llama: Integrating LLMs into Streamable Transducer-based Speech Recognition
2025
Transducer-Llama: Integrating LLMs into Streamable Transducer-based Speech Recognition
arXiv (Cornell University)·2024Open Access
Get Large Language Models Ready to Speak: A Late-fusion Approach for Speech Generation
arXiv (Cornell University)·2024Open Access
Improving Spoken Semantic Parsing using Synthetic Data from Large Generative Models
2024Open Access
Effective internal language model training and fusion for factorized transducer model
arXiv (Cornell University)·2024Open Access
Prompting Large Language Models with Speech Recognition Abilities
2024· 77 cited
TODM: Train Once Deploy Many Efficient Supernet-Based RNN-T Compression For On-Device ASR Models
2024· 1 cited
Effective Internal Language Model Training and Fusion for Factorized Transducer Model
2024· 1 cited
AudioChatLlama: Towards General-Purpose Speech Abilities for LLMs
2024· 15 citedOpen Access
AudioChatLlama: Towards General-Purpose Speech Abilities for LLMs
arXiv (Cornell University)·2023Open Access
TODM: Train Once Deploy Many Efficient Supernet-Based RNN-T Compression For On-device ASR Models
arXiv (Cornell University)·2023Open Access
Multi-Head State Space Model for Speech Recognition
2023· 7 cited
Prompting Large Language Models with Speech Recognition Abilities
arXiv (Cornell University)·2023· 2 citedOpen Access
Multi-Head State Space Model for Speech Recognition
arXiv (Cornell University)·2023· 1 citedOpen Access
Dynamic Speech Endpoint Detection with Regression Targets
2023· 4 cited
Dynamic Speech Endpoint Detection with Regression Targets
arXiv (Cornell University)·2022Open Access
Streaming Transformer Transducer based Speech Recognition Using Non-Causal Convolution
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)·2022· 13 cited
page 1 of 2Next →

Frequent Co-authors

Ozlem Kalinli(16), Jay Mahadeokar(15), Chunyang Wu(11), Yuan Shangguan(10), Yangyang Shi(9), Yassir Fathullah(8), Junteng Jia(8), Dong Yu(6), Jinxi Guo(6), Christian Fuegen(6), Jasha Droppo(4), Frank Seide(4), Chunyang Wu(4), Julian Chan(4), Frank Zhang(4), Egor Lakomkin(4), Wenhan Xiong(4), Dilin Wang(4), Chunxi Liu(4), Niko Moritz(4)