Michael L. Seltzer
- Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion
2021/04/05 by Duc Le, Le, Duc, Mahaveer Jain +21 · 22 citations
Computer Science · #Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Natural Language Processing Techniques #Speech Recognition and Synthesis #Topic Modeling #electronic engineering #information engineering
- Semantic Distance: A New Metric for ASR Performance Analysis Towards Spoken Language Understanding
2021/04/05 by Suyoun Kim, Kim, Suyoun, Abhinav Arora +11 · 12 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Speech Recognition and Synthesis #Topic Modeling
- End-to-End Speech Recognition Contextualization with Large Language Models
2023/09/19 by Egor Lakomkin, Chunyang Wu, Lakomkin, Egor +9 · 12 citations
Computer Science · #Speech Recognition and Synthesis #Natural Language Processing Techniques #Topic Modeling
- Towards measuring fairness in speech recognition: Fair-Speech dataset
2024/08/22 by Irina-Elena Veliche, Zhuangqun Huang, Veliche, Irina-Elena +9 · 15 citations
Computer Science · #Artificial Intelligence (cs.AI) #Audio and Speech Processing (eess.AS) #Computers and Society (cs.CY) #FOS: Computer and information sciences #FOS: Electrical engineering #Hate Speech and Cyberbullying Detection #Machine Learning (stat.ML) #Sound (cs.SD) #electronic engineering #information engineering
- Massively Multilingual ASR on 70 Languages: Tokenization, Architecture, and Generalization Capabilities
2022/11/10 by Andros Tjandra, Nayan Singhal, Tjandra, Andros +11 · 6 citations
Computer Science · #Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Electrical engineering #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Sound (cs.SD) #Speech and dialogue systems #electronic engineering #information engineering
- End-to-end contextual speech recognition using class language models and a token passing decoder
2018/12/05 by Zhehuai Chen, Mahaveer Jain, Chen, Zhehuai +7 · 2 citations
Computer Science · #68T10 #Computation and Language (cs.CL) #FOS: Computer and information sciences #I.2.7 #Machine Learning (cs.LG) #Natural Language Processing Techniques #Speech Recognition and Synthesis #Topic Modeling
- Improved training for online end-to-end speech recognition systems
2017/11/06 by Suyoun Kim, Kim, Suyoun, Michael L. Seltzer +5 · 1 citation
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Speech Recognition and Synthesis #Speech and Audio Processing #Speech and dialogue systems
- Feature Learning in Deep Neural Networks - Studies on Speech Recognition\n Tasks
2013/01/16 by Dong Yu, Michael L. Seltzer, Yu, Dong +7 · 1 citation
Computer Science · #Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Music and Audio Processing #Natural Language Processing Techniques #Neural and Evolutionary Computing (cs.NE) #Speech Recognition and Synthesis #Speech and Audio Processing #electronic engineering #information engineering
- Dynamic Encoder Transducer: A Flexible Solution For Trading Off Accuracy For Latency
2021/04/05 by Yangyang Shi, Shi, Yangyang, Varun Nagaraja +21 · 1 citation
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Music and Audio Processing #Speech Recognition and Synthesis #Speech and Audio Processing
- Factorized Blank Thresholding for Improved Runtime Efficiency of Neural Transducers
2022/11/02 by Manh Duc Le, Frank Seide, Le, Duc +11 · 1 citation
Computer Science · Earth and Planetary Sciences · #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Neural Networks and Applications #Sound (cs.SD) #Speech Recognition and Synthesis #Underwater Acoustics Research #electronic engineering #information engineering
- Improving Fast-slow Encoder based Transducer with Streaming Deliberation
2022/12/15 by Ke Li, Li, Ke, Jay Mahadeokar +13 · 1 citation
Computer Science · Engineering · #Audio and Speech Processing (eess.AS) #FOS: Electrical engineering #Speech Recognition and Synthesis #Speech and Audio Processing #Ultrasonics and Acoustic Wave Propagation #electronic engineering #information engineering