Filter Results:
- Full text PDF available (40)
Publication Year
1999
2018
- This year (21)
- Last 5 years (64)
- Last 10 years (101)
Publication Type
Co-author
Journals and Conferences
Learn More
- Daniel Povey, Arnab Ghoshal, +10 authors Karel Veselý
- 2011
We describe the design of Kaldi, a free, open-source toolkit for speech recognition research. Kaldi provides a speech recognition system based on finite-state transducers (using the freely available… (More)
- Daniel Povey
- 2003
- Daniel Povey, Philip C. Woodland
- 2002 IEEE International Conference on Acoustics…
- 2002
In this paper we introduce the Minimum Phone Error (MPE) and Minimum Word Error (MWE) criteria for the discriminative training of HMM systems. The MPE/MWE criteria are smoothed approximations to the… (More)
- Daniel Povey, Dimitri Kanevsky, Brian Kingsbury, Bhuvana Ramabhadran, George Saon, Karthik Visweswariah
- 2008 IEEE International Conference on Acoustics…
- 2008
We present a modified form of the maximum mutual information (MMI) objective function which gives improved results for discriminative training. The modification consists of boosting the likelihoods… (More)
- Vassil Panayotov, Guoguo Chen, Daniel Povey, Sanjeev Khudanpur
- 2015 IEEE International Conference on Acoustics…
- 2015
This paper introduces a new corpus of read English speech, suitable for training and evaluating speech recognition systems. The LibriSpeech corpus is derived from audiobooks that are part of the… (More)
- Daniel Povey, Lukás Burget, +10 authors Samuel Thomas
- Computer Speech & Language
- 2011
We describe a new approach to speech recognition, in which all Hidden Markov Model (HMM) states share the same Gaussian Mixture Model (GMM) structure with the same number of Gaussians in each state.… (More)
- Philip C. Woodland, Daniel Povey
- Computer Speech & Language
- 2002
- Daniel Povey, Vijayaditya Peddinti, +5 authors Sanjeev Khudanpur
- INTERSPEECH
- 2016
In this paper we describe a method to perform sequencediscriminative training of neural network acoustic models without the need for frame-level cross-entropy pre-training. We use the lattice-free… (More)
- Vijayaditya Peddinti, Daniel Povey, Sanjeev Khudanpur
- INTERSPEECH
- 2015
Recurrent neural network architectures have been shown to efficiently model long term temporal dependencies between acoustic events. However the training time of recurrent networks is higher than… (More)
- Karel Veselý, Arnab Ghoshal, Lukás Burget, Daniel Povey
- INTERSPEECH
- 2013
Sequence-discriminative training of deep neural networks (DNNs) is investigated on a standard 300 hour American English conversational telephone speech task. Different sequencediscriminative criteria… (More)