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 phoneme set influence for Lithuanian speech commands recognition accuracy is investigated. Four phoneme sets are discussed. LIEPA speech corpus for training of Acoustic Model is used. The phonetic representation of corpus transcriptions is generated by grapheme-to-phoneme transformation rules. Rule based transformations for Lithuanian language is proposed. Recognition engine with CMU Pocketsphinx...
DNN based acoustic models require a large amount of training data. Parametric data augmentation techniques such as adding noise, reverberation, or changing the speech rate, are often employed to boost the dataset size and the ASR performance. The choice of augmentation techniques and the associated parameters has been handled heuristically so far. In this work we propose an algorithm to automatically...
Aphasia is a type of acquired language impairment caused by brain injury. This paper presents an automatic speech recognition (ASR) based approach to objective assessment of aphasia patients. A dedicated ASR system is developed to facilitate acoustical and linguistic analysis of Cantonese aphasia speech. The acoustic models and the language models are trained with domain- and style-matched speech...
End-to-end speech recognition systems have been successfully implemented and have become competitive replacements for hybrid systems. A common loss function to train end-to-end systems is connectionist temporal classification (CTC). This method maximizes the log likelihood between the feature sequence and the associated transcription sequence. However there are some weaknesses with CTC training. The...
It has been shown that by combining the acoustic and articulatory information significant performance improvements in automatic speech recognition (ASR) task can be achieved. In practice, however, articulatory information is not available during recognition and the general approach is to estimate it from the acoustic signal. In this paper, we propose a different approach based on the generalized distillation...
Based on the relationship between porosity (or lithological facies) and other petrophysical properties, Artificial neural networks (ANN) are respectively trained for porosity estimation and lithological facies classification, using core porosity (CPOR) data and core lithological facies interpretation results of part of core interval together with some well logs (petrophysical properties). After the...
In this paper we study the impact of phonetic annotation precision on the accuracy of a state-of-the art ASR (automatic speech recognition) system. This issue becomes important especially if we want to port the system to a new language without spending much time by collecting, checking and annotating a large amount of acoustic data in the target language. First, we describe a series of experiments...
Convolutional Neural Networks (CNNs) have demonstrated powerful acoustic modelling capabilities due to their ability to account for structural locality in the feature space; and in recent works CNNs have been shown to often outperform fully connected Deep Neural Networks (DNNs) on TIMIT and LVCSR. In this paper, we perform a detailed empirical study of CNNs under the low resource condition, wherein...
This paper introduces a method to produce high-quality transcriptions of speech data from only two crowd-sourced transcriptions. These transcriptions, produced cheaply by people on the Internet, for example through Amazon Mechanical Turk, are often of low quality. Often, multiple crowd-sourced transcriptions are combined to form one transcription of higher quality. However, the state of the art is...
This paper describes the French broadcast speech transcription system by CRIM for the ETAPE 2011 evaluation. The key elements in this recognizer include over 140,000-word dictionary, 478 hours of audio for training the acoustic models, feature-space MMI and boosted MMI discriminative training of the acoustic models, variable-frame-rate decoding with trigram language model, lattice rescoring with quadgram...
This paper deals with the evaluation of grapheme-to-phoneme (G2P) converters in a speech recognition context. The precision and recall rates are investigated as potential measures of the quality of the multiple generated pronunciation variants. Very different results are obtained whether or not we take into account the frequency of occurrence of the words. Since G2P systems are rarely evaluated on...
In this paper, we consider the issue of speaker identification within audio records of broadcast news. The speaker identity information is extracted from both transcript-based and acoustic-based speaker identification systems. This information is combined in the belief functions framework, which makes coherent the knowledge representation of the problem. The Kuhn-Munkres algorithm is used to optimize...
Modern speech applications utilize acoustic models with billions of parameters, and serve millions of users. Storing an acoustic model for each user is costly. We show through the use of sparse regularization, that it is possible to obtain competitive adaptation performance by changing only a small fraction of the parameters of an acoustic model. This allows for the compression of speaker-dependent...
One of the goals of Speech Recognition Security (SRS) systems is to have appropriately tools to recognize speech password spoken based on elements such as words, sub-word or speakers. The main goal of the present work is to design robust ASR systems based on alternative ways to the classical evaluation rates, which often depend on the vocabulary of the task and on the language resources available...
Acoustic modeling using mixtures of multivariate Gaussians is the prevalent approach for many speech processing problems. Computing likelihoods against a large set of Gaussians is required as a part of many speech processing systems and it is the computationally dominant phase for LVCSR systems. We express the likelihood computation as a multiplication of matrices representing augmented feature vectors...
The development of automatic speech recognition (ASR) technology in recent years has made it possible for some intelligent query systems to use a voice interface. Automatic song selection is a practical and interesting application of ASR. In this paper we describe our efforts to build and improve a Chinese song name recognition system. It is a large vocabulary, speaker-independent system currently...
We describe a new approach for phoneme recognition which aims at minimizing the phoneme error rate. Building on structured prediction techniques, we formulate the phoneme recognizer as a linear combination of feature functions. We state a PAC-Bayesian generalization bound, which gives an upper-bound on the expected phoneme error rate in terms of the empirical phoneme error rate. Our algorithm is derived...
In this paper we report our recent development of an end-to-end integrative design methodology for speech translation. Specifically, a novel decision function is proposed based on the Bayesian analysis, and the associated discriminative learning technique is presented based on the decision-feedback principle. The decision function in our end-to-end design methodology integrates acoustic scores, language...
Neural networks are a useful alternative to Gaussian mixture models for acoustic modeling; however, training multilayer networks involves a difficult, nonconvex optimization that requires some “art” to make work well in practice. In this paper we investigate the use of arccosine kernels for speech recognition, using these kernels in a hybrid support vector machine/hidden Markov model recognition system...
In this paper, the task of selecting the optimal subset of pronunciation variants from a set of automatically generated candidates is recast as a tree search problem. In this approach, the optimal recognition lexicon corresponds with the optimal path through a search tree. We define a discriminative evaluation function to guide the search algorithm, which is based on estimates of the number of recognition...
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.