The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
A driver is regarded as a system that receives visual information and that controls the steering wheel. To identify the system, we conducted experiments to get input-output data using a driving simulator and confirmed that the focus of expansion of optical flow has sufficient information to predict steering behaviors.
This paper proposes a cascading deep neural network (DNN) structure for speech synthesis system that consists of text-to-bottleneck (TTB) and bottleneck-to-speech (BTS) models. Unlike conventional single structure that requires a large database to find complicated mapping rules between linguistic and acoustic features, the proposed structure is very effective even if the available training database...
We propose two simple methods to improve the performance of a keyword spotting system. In our application, the users are allowed to change the keywords anytime if they want. Thus we focused on phone-based GMM-HMM models since they do not require keyword-specific training data. However, the GMM-HMM based models usually have very high false alarm rate, i.e., a keyword is not present but the system gives...
Recently, deep and/or recurrent neural networks (DNNs/RNNs) have been employed for voice conversion, and have significantly improved the performance of converted speech. However, DNNs/RNNs generally require a large amount of parallel training data (e.g., hundreds of utterances) from source and target speakers. It is expensive to collect such a large amount of data, and impossible in some applications,...
This paper proposes an ensemble based automatic speaker recognition (ASV) using adapted score fusion in noisy reverberant environment. It is well known that background noise and reverberation affect the performance of the ASV systems. Various techniques have been reported to improve the robustness against noise and reverberation, and an ensemble based method is one of the effective techniques in the...
Training very deep neural networks is very difficult because of gradient degradation. However, the incomparable expressiveness of the many deep layers is highly desirable at testing time and usually leads to better performance. Recently, training techniques such as residual networks that enable us to train very deep networks have proved to be a great success. In this paper, we studied the application...
I-vector adaptation of DNN-HMM acoustic models has shown clear performance improvement for speech recognition. In this paper, we study this technique on Babel task. we use Swahili as target language (training data of 50 hours) and another 6 languages as multilingual resources to train i-vector extractors respectively. Our study shows that i-vector extractors trained with more multilingual data only...
Optical flow is one of the key components in computer vision research area. Since the seminal work proposed by Horn and Schunck [1], numerous advanced algorithms have been proposed. Many state-of-the-art optical flow estimation algorithms optimize the data and regularization terms to solve ill-posed problems. However, despite their major advances over last decade, conventional optical flow methods...
This paper describes our scheme to translate spoken English lectures into Japanese consisting of an English automatic speech recognition system (ASR) that utilizes a deep neural network (DNN) and an English to Japanese phrase-based statistical machine translation system (SMT). We focused on domain adaptation of the acoustic and translation models. For domain adaptation of the translation model, frequently...
We attempt to formulate Bayesian speaker adaptation for deep models and explore two different solutions. In the first “indirect” approach, Bayesian adaptation is applied to context-dependent, Gaussian-mixture-model based hidden Markov models (CD-GMM-HMMs) with bottleneck (BN) features derived from deep neural networks (DNNs). The second method directly formulates Bayesian adaptation for CD-DNN-HMMs...
For text-independent short-utterance speaker recognition (SUSR), the performance often degrades dramatically. This paper presents a combination approach to the SUSR tasks with two phonetic-aware systems: one is the DNN-based i-vector system and the other is our recently proposed subregion-based GMM-UBM system. The former employs phone posteriors to construct an i-vector model in which the shared statistics...
Wireless sensor networks (WSNs) were designed for monitoring environment that is difficult to access. The energy of each node has its limit and cannot be replaced or recharged. All components of WSNs must be an energy efficient component, not only hardware component but also software component. Energy efficient routing protocol can prolong the networks lifetime. Reactive WSNs is addressed in this...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.