In this paper, we consider the use of multiple acoustic features of the speech signal for robust speech recognition. We investigate the combination of various auditory based (Mel Frequency Cepstrum Coefficients, Perce...
详细信息
We present a novel confidence-based discriminative training for model adaptation approach for an HMM based Arabic handwriting recognition system to handle different handwriting styles and their variations. Most curren...
详细信息
The most widely used acoustic feature extraction methods of current automatic speech recognition (ASR) systems are based on the assumption of stationarity. In this paper we extensively evaluate a recently introduced f...
详细信息
Handwritten Text recognition experiments and results are presented on the historical Bentham text image dataset used in the ICFHR-2014 HTRtS competition. The successful segmentation-free holistic framework is adopted,...
详细信息
On dedicated websites, people can upload videos and share it with the rest of the world. Currently these videos are categorized manually by the help of the user community. In this paper, we propose a combination of co...
详细信息
In this paper, three different voicing features are studied as additional acoustic features for continuous speech recognition. The harmonic product spectrum based feature is extracted in frequency domain while the aut...
详细信息
In this paper, three different voicing features are studied as additional acoustic features for continuous speech recognition. The harmonic product spectrum based feature is extracted in frequency domain while the autocorrelation and the average magnitude difference based methods work in time domain. The algorithms produce a measure of voicing for each time frame. The voicing measure was combined with the standard Mel Frequency Cepstral Coefficients (MFCC) using linear discriminant analysis to choose the most relevant features. Experiments have been performed on small and large vocabulary tasks. The three different voicing measures combined with MFCCs resulted in similar improvements in word error rate: improvements of up to 14% on the small-vocabulary task and improvements of up to 6% on the large-vocabulary task relative to using MFCC alone with the same overall number of parameters in the system.
Current neural translation networks are based on an effective attention mechanism that can be considered as an implicit probabilistic notion of alignment. Such architectures do not guarantee a high quality alignment, ...
详细信息
Despite the advances achieved by neural models in sequence to sequence learning, exploited in a variety of tasks, they still make errors. In many use cases, these are corrected by a human expert in a posterior revisio...
详细信息
Current machine translation systems require human revision to produce high-quality translations. This is achieved through a post-editing process or by means of an interactive human-computer collaboration. Most protoco...
详细信息
Manual analysis and decryption of enciphered documents is a tedious and error prone work. Often-even after spending large amounts of time on a particular cipher-no decipherment can be found. Automating the decryption ...
详细信息
暂无评论