1 |
Effect and Analysis of Large-scale Language Model Rescoring on Competitive ASR Systems ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Single headed attention based sequence-to-sequence model for state-of-the-art results on Switchboard ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Challenging the Boundaries of Speech Recognition: The MALACH Corpus ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Building competitive direct acoustics-to-word models for English conversational speech recognition ...
|
|
|
|
Abstract:
Direct acoustics-to-word (A2W) models in the end-to-end paradigm have received increasing attention compared to conventional sub-word based automatic speech recognition models using phones, characters, or context-dependent hidden Markov model states. This is because A2W models recognize words from speech without any decoder, pronunciation lexicon, or externally-trained language model, making training and decoding with such models simple. Prior work has shown that A2W models require orders of magnitude more training data in order to perform comparably to conventional models. Our work also showed this accuracy gap when using the English Switchboard-Fisher data set. This paper describes a recipe to train an A2W model that closes this gap and is at-par with state-of-the-art sub-word based models. We achieve a word error rate of 8.8%/13.9% on the Hub5-2000 Switchboard/CallHome test sets without any decoder or language model. We find that model initialization, training data order, and regularization have the most ... : Submitted to IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018 ...
|
|
Keyword:
Artificial Intelligence cs.AI; Computation and Language cs.CL; FOS Computer and information sciences; Machine Learning stat.ML; Neural and Evolutionary Computing cs.NE
|
|
URL: https://dx.doi.org/10.48550/arxiv.1712.03133 https://arxiv.org/abs/1712.03133
|
|
BASE
|
|
Hide details
|
|
16 |
Binary Pattern Recognition Using Markov Random Fields and HMMs
|
|
|
|
In: IEEE International Conference on Acoustics, Speech, and Signal Processing - ICASSP 1997 ; https://hal.inria.fr/inria-00537357 ; IEEE International Conference on Acoustics, Speech, and Signal Processing - ICASSP 1997, Apr 1997, Munich, Germany. pp.3725 - 3728, ⟨10.1109/ICASSP.1997.604678⟩ ; http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=604678 (1997)
|
|
BASE
|
|
Show details
|
|
17 |
Off-line Handwritten Word Recognition Using a Mixed HMM-MRF Approach
|
|
|
|
In: 4th International Conference on Document Analysis and Recognition - ICDAR'97 ; https://hal.inria.fr/inria-00537568 ; 4th International Conference on Document Analysis and Recognition - ICDAR'97, Aug 1997, Ulm, Germany. pp.118 - 122, ⟨10.1109/ICDAR.1997.619825⟩ ; http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=619825 (1997)
|
|
BASE
|
|
Show details
|
|
18 |
One and two-dimensional Markov models for off-line handwriting recognition ; Modèles markoviens uni- et bidimensionnels pour la reconnaissance de l'écriture manuscrite hors-ligne
|
|
|
|
In: https://hal.univ-lorraine.fr/tel-01747325 ; Autre [cs.OH]. Université Henri Poincaré - Nancy 1, 1997. Français. ⟨NNT : 1997NAN10299⟩ (1997)
|
|
BASE
|
|
Show details
|
|
19 |
Modèles markoviens uni- et bidimensionnels pour la reconnaissance de l'écriture manuscrite hors-ligne ; One and two-dimensional Markov models for off-line handwriting recognition
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Off-Line Handwriting Recognition by Statistical Correlation
|
|
|
|
In: IAPR Workshop on Machine Vision Applications - MVA'94 ; https://hal.inria.fr/inria-00533959 ; IAPR Workshop on Machine Vision Applications - MVA'94, IAPR, Dec 1994, Kawasaki, Japan. pp.371-374 ; http://b2.cvl.iis.u-tokyo.ac.jp/mva/proceedings/CommemorativeDVD/1994/papers/1994371.pdf (1994)
|
|
BASE
|
|
Show details
|
|
|
|