Multifeature Modular Deep Neural Network Acoustic Models
نویسندگان
چکیده
This paper presents and examines multifeature modular deep neural network acoustic models. The proposed setup uses well trained bottleneck networks to extract features from multiple combinations of input features and combines them using a classification deep neural network (DNN). The effectiveness of each feature combination is evaluated empirically on multiple test sets for both a classical DNN as well as a for modular DNNs using only a single module. Modular DNNs using two or more modules are shown to reduce the WER by up to 11.5% relatively compared to a baseline DNN and give the best overall performance on both test sets.
منابع مشابه
معرفی شبکه های عصبی پیمانه ای عمیق با ساختار فضایی-زمانی دوگانه جهت بهبود بازشناسی گفتار پیوسته فارسی
In this article, growable deep modular neural networks for continuous speech recognition are introduced. These networks can be grown to implement the spatio-temporal information of the frame sequences at their input layer as well as their labels at the output layer at the same time. The trained neural network with such double spatio-temporal association structure can learn the phonetic sequence...
متن کاملشبکه عصبی پیچشی با پنجرههای قابل تطبیق برای بازشناسی گفتار
Although, speech recognition systems are widely used and their accuracies are continuously increased, there is a considerable performance gap between their accuracies and human recognition ability. This is partially due to high speaker variations in speech signal. Deep neural networks are among the best tools for acoustic modeling. Recently, using hybrid deep neural network and hidden Markov mo...
متن کاملModular combination of deep neural networks for acoustic modeling
In this work, we propose a modular combination of two popular applications of neural networks to large-vocabulary continuous speech recognition. First, a deep neural network is trained to extract bottleneck features from frames of mel scale filterbank coefficients. In a similar way as is usually done for GMM/HMM systems, this network is then applied as a nonlinear discriminative feature-space t...
متن کاملPersian Phone Recognition Using Acoustic Landmarks and Neural Network-based variability compensation methods
Speech recognition is a subfield of artificial intelligence that develops technologies to convert speech utterance into transcription. So far, various methods such as hidden Markov models and artificial neural networks have been used to develop speech recognition systems. In most of these systems, the speech signal frames are processed uniformly, while the information is not evenly distributed ...
متن کاملCombining pattern recognition and deep-learning-based algorithms to automatically detect commercial quadcopters using audio signals (Research Article)
Commercial quadcopters with many private, commercial, and public sector applications are a rapidly advancing technology. Currently, there is no guarantee to facilitate the safe operation of these devices in the community. Three different automatic commercial quadcopters identification methods are presented in this paper. Among these three techniques, two are based on deep neural networks in whi...
متن کامل