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.
The vocabulary is a vital component of automatic speech recognition(ASR) systems. For a specific Chinese speech recognition task, using a large general vocabulary not only leads to a much longer time to decode, but also hurts the recognition accuracy. In this paper, we proposed an unsupervised algorithm to select task-specific words from a large general vocabulary. The out-of-vocabulary(OOV) rate...
Link prediction in networks is of both theoretical interest and practical significance in many branches of science, and a great number of algorithms are based on microscale (common neighbours) or mesoscale (communities) information of observed networks. Either microscale or mesoscale methods are limited in the understanding of the topological properties at the corresponding scales. This article proposes...
Link prediction has significance in both theoretical interest and practical operation. Many methods via local and global structural information have been proposed. Methods based on local information like the Common Neighbours Index(CN) successfully reduce the computational expense but suffer from poor prediction performance. In this article, we put forward a new approach, namely Betweenness and Common...
Training acoustic models for ASR requires large amounts of labelled data which is costly to obtain. Hence it is desirable to make use of unlabelled data. While unsupervised training can give gains for standard HMM training, it is more difficult to make use of unlabelled data for discriminative models. This paper explores semi-supervised training of Deep Neural Networks (DNN) in a meeting recognition...
The detection of Out-of-vocabulary (OOV) words is a crucial problem for spoken term detection (STD). In this paper, the use of integration with local acoustic information is investigated to retrieve more OOV words. Tokens with high local acoustic probabilities propagated in the search space at the decoding stage will be forced to propagate to the next frame. In this way, acoustic similar words can...
This paper presents an investigation of far field speech recognition using beamforming and channel concatenation in the context of Deep Neural Network (DNN) based feature extraction. While speech enhancement with beamforming is attractive, the algorithms are typically signal-based with no information about the special properties of speech. A simple alternative to beamforming is concatenating multiple...
Based on the set pair analysis (SPA) and the variable fuzzy sets theory, In order to simplify the evaluation procedure of relative difference degree and make the accurate evaluation of the the integrity of pile foundation quantitatively, a new variable fuzzy set model for evaluation of integrity of pile foundation was established. Moreover, it was shown by comparison of results between a practical...
Keyword spotting becomes a very important branch of speech recognition. But the acoustic mismatch between training and testing environments often causes a severe degradation in the recognition performance. This paper presents an improved keyword spotting strategy. A fuzzy search algorithm is proposed to extract keyword hypotheses from a syllable confusion network (SCN). SCN is linear and naturally...
This paper presents an approach to tone recognition in mandarin conversational telephone speech (CTS) based on a real context model. The real context model is proposed as a new concept designed with special consideration on the fact that mandarin CTS is characterized by complicated tone behaviors due to physiological articulation. As pitch is a supra-segmental feature, current tone's pitch value is...
Keyword spotting becomes a very important branch of speech recognition. But the acoustic mismatch between training and testing environments often causes a severe degradation in the recognition performance. This paper presents an improved keyword spotting strategy. A fuzzy search algorithm is proposed to extract keyword hypotheses from a syllable confusion network (SCN). SCN is linear and naturally...
This paper presents an approach to tone recognition in mandarin conversational telephone speech (CTS) based on a real context model. The real context model is proposed as a new concept designed with special consideration on the fact that mandarin CTS is characterized by complicated tone behaviors due to physiological articulation. As pitch is a supra-segmental feature, current tone's pitch value is...
This paper presents a fast vocabulary-independent audio search method in Mandarin spontaneous speech which is based on syllable confusion network (SCN) indexing. Confusion network is linear and naturally suitable for indexing. The feasibility of using syllable confusion network as lattice representation is firstly investigated. Since direct syllabic decoding may not have a very high accuracy, long-...
For many practical applications of keyword spotting, input signal is a spontaneous conversation. Generally speaking, keyword spotting system will degrade significantly because of mismatch between acoustic model and speech. To solve this problem, this paper presents a two-pass based keyword spotting strategy. Different from one-pass based system, decoding process is done in the whole acoustic space,...
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.