← Authors

Daniel Povey

48 papers · 2012–2025 · 4 conferences · across top CS/AI conferences

Achievements

🧭 Keyword Pioneer 🐣 Hot Topic Early Bird πŸƒ Academic Marathon (13) 🌈 Renaissance Researcher (5) πŸŒ‰ Interdisciplinary Bridge 🌍 Conference Polyglot (4) 🐝 Cross-Pollinator (9) πŸ—ΊοΈ Taxonomy Completionist (23) 🏠 Conference Loyalist (44) πŸ† Keyword Champion (3) 🧬 Topic Evolution πŸ‘₯ Mega-Team (20) πŸ”¬ Deep Specialist (19) 🀝 Dynamic Duo (36) πŸš€ Conference Pioneer πŸ”₯ Unstoppable (11) ⚑ Prolific Year (5) πŸ’Ž Century Club (48) πŸ—ƒοΈ Keyword Collector (95) πŸ“ˆ Trend Setter

Conferences

INTERSPEECH (44) ICLR (2) AISTATS (1) EMNLP (1)

Top co-authors

Sanjeev Khudanpur (36) Yiming Wang (10) David Snyder (8) Vimal Manohar (8) Hainan Xu (7) Pegah Ghahremani (7) Wei Kang (6) Zengwei Yao (6) Long Lin (6) Fangjun Kuang (6)

Keywords

automatic speech recognition (13) deep neural network (10) word error rate (6) speaker diarization (5) speaker recognition (5) speech recognition (5) connectionist temporal classification (4) speaker embedding (4) probabilistic linear discriminant analysis (4) neural transducer (3) neural network (3) acoustic modeling (3) speaker verification (3) acoustic model (3) time delay neural network (3) lattice-free maximum mutual information (3) feature extraction (3) stochastic gradient descent (2) temporal modeling (2) speech corpus (2)

Papers

CR-CTC: Consistency regularization on CTC for improved speech recognition ICLR 2025
LibriheavyMix: A 20,000-Hour Dataset for Single-Channel Reverberant Multi-Talker Speech Separation, ASR and Speaker Diarization INTERSPEECH 2024
Multi-Channel Multi-Speaker ASR Using Target Speaker’s Solo Segment INTERSPEECH 2024
Zipformer: A faster and better encoder for automatic speech recognition ICLR 2024
Enhancing Neural Transducer for Multilingual ASR with Synchronized Language Diarization INTERSPEECH 2024
Improving Neural Biasing for Contextual Speech Recognition by Early Context Injection and Text Perturbation INTERSPEECH 2024
Bypass Temporal Classification: Weakly Supervised Automatic Speech Recognition with Imperfect Transcripts INTERSPEECH 2023
Blank-regularized CTC for Frame Skipping in Neural Transducer INTERSPEECH 2023
GPU-accelerated Guided Source Separation for Meeting Transcription INTERSPEECH 2023
Delay-penalized CTC Implemented Based on Finite State Transducer INTERSPEECH 2023
Pruned RNN-T for fast, memory-efficient ASR training INTERSPEECH 2022
speechocean762: An Open-Source Non-Native English Speech Corpus for Pronunciation Assessment INTERSPEECH 2021
GigaSpeech: An Evolving, Multi-Domain ASR Corpus with 10,000 Hours of Transcribed Audio INTERSPEECH 2021
An Alternative to MFCCs for ASR INTERSPEECH 2020
Efficient MDI Adaptation for n-Gram Language Models INTERSPEECH 2020
Lattice-Free Maximum Mutual Information Training of Multilingual Speech Recognition Systems INTERSPEECH 2020
Wake Word Detection with Alignment-Free Lattice-Free MMI INTERSPEECH 2020
Neural Language Modeling with Implicit Cache Pointers INTERSPEECH 2020
PyChain: A Fully Parallelized PyTorch Implementation of LF-MMI for End-to-End ASR INTERSPEECH 2020
Improving Emotion Identification Using Phone Posteriors in Raw Speech Waveform Based DNN INTERSPEECH 2019
Advances in Automatic Speech Recognition for Child Speech Using Factored Time Delay Neural Network INTERSPEECH 2019
Multi-PLDA Diarization on Children’s Speech INTERSPEECH 2019
State-of-the-Art Speaker Recognition for Telephone and Video Speech: The JHU-MIT Submission for NIST SRE18 INTERSPEECH 2019
x-Vector DNN Refinement with Full-Length Recordings for Speaker Recognition INTERSPEECH 2019
Speaker Recognition Benchmark Using the CHiME-5 Corpus INTERSPEECH 2019
The JHU Speaker Recognition System for the VOiCES 2019 Challenge INTERSPEECH 2019
The JHU ASR System for VOiCES from a Distance Challenge 2019 INTERSPEECH 2019
Self-Attentive Speaker Embeddings for Text-Independent Speaker Verification INTERSPEECH 2018
Output-Gate Projected Gated Recurrent Unit for Speech Recognition INTERSPEECH 2018
Acoustic Modeling from Frequency Domain Representations of Speech INTERSPEECH 2018
End-to-end Deep Neural Network Age Estimation INTERSPEECH 2018
End-to-end Speech Recognition Using Lattice-free MMI INTERSPEECH 2018
Recurrent Neural Network Language Model Adaptation for Conversational Speech Recognition INTERSPEECH 2018
Semi-Orthogonal Low-Rank Matrix Factorization for Deep Neural Networks INTERSPEECH 2018
Emotion Identification from Raw Speech Signals Using DNNs INTERSPEECH 2018
Diarization is Hard: Some Experiences and Lessons Learned for the JHU Team in the Inaugural DIHARD Challenge INTERSPEECH 2018
A GPU-based WFST Decoder with Exact Lattice Generation INTERSPEECH 2018
An Exploration of Dropout with LSTMs INTERSPEECH 2017
Phone Duration Modeling for LVCSR Using Neural Networks INTERSPEECH 2017
Deep Neural Network Embeddings for Text-Independent Speaker Verification INTERSPEECH 2017
Backstitch: Counteracting Finite-Sample Bias via Negative Steps INTERSPEECH 2017
The Kaldi OpenKWS System: Improving Low Resource Keyword Search INTERSPEECH 2017
Acoustic Data-Driven Lexicon Learning Based on a Greedy Pronunciation Selection Framework INTERSPEECH 2017
Acoustic Modelling from the Signal Domain Using CNNs INTERSPEECH 2016
Far-Field ASR Without Parallel Data INTERSPEECH 2016
Purely Sequence-Trained Neural Networks for ASR Based on Lattice-Free MMI INTERSPEECH 2016
A Coarse-Grained Model for Optimal Coupling of ASR and SMT Systems for Speech Translation EMNLP 2015
Krylov Subspace Descent for Deep Learning AISTATS 2012