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.
In this paper, we investigate various training methods for building deep neural network (DNN) based acoustic models for dysarthric speech data. Methods like multitask learning, knowledge distillation and model adaptation, which overcome data sparsity and model over-fitting problems are employed to study the merits of each method. In Knowledge distillation framework, some privilege information in addition...
Automatic speech recognition can be used to evaluate the accuracy of read speech and thus serve a valuable role in literacy development by providing the needed feedback on reading skills in the absence of qualified teachers. Given the known limitations of ASR in the face of insufficient task-specific training data, the selection of acoustic and language modeling strategies can play a crucial role...
There are several challenges while building Automatic Speech Recognition (ASR) system for low resource languages such as Indic languages. One problem is the access to large amounts of training data required to build Acoustic Models (AM) from scratch. In the context of Indian English, another challenge encountered is code-mixing as many Indian speakers are multilingual and exhibit code-mixing in their...
Speech uttered by the human beings contains the information about speakers, languages and contents. Language of uttered speech can easily be identified by extracting the language specific information from it. Identification of language of speech is known as Language Identification (LID). Identification of language from speech is helpful in its translation, speech recognition and speech activated automatic...
As the presentation slides are of vital importance in a person's career, a significant amount of time is spent for its preparation. An automatic paper-summarizer will reduce the amount of time and human effort. Presently, tools exist for formatting and designing themes for slides, but not for content generation. This paper proposes a summarization system that automatically generates presentation slides...
The trend for about twenty years, the research regarding the number of states in Hidden Markov Model (HMM) was mainly aimed at increasing it in order to ensure the robustness of the face recognition system. In this paper, a novel face recognition method is presented based on one state of discrete HMM, where it seemed impossible in the past. Contrary to other approaches that use the three parameters...
We consider the extraction of information from broadcast radio speech in Uganda for the purposes of informing relief and development programmes by the United Nations. Although internet penetration in Uganda is low, mobile phones are ubiquitous and have made radio a vibrant medium for interactive public discussion. Vulnerable groups make use of radio to discuss issues related to, for example, agriculture,...
We examine the effect of the Group Lasso (gLasso) regularizer in selecting the salient nodes of Deep Neural Network (DNN) hidden layers by applying a DNN-HMM hybrid speech recognizer to TED Talks speech data. We test two types of gLasso regularization, one for outgoing weight vectors and another for incoming weight vectors, as well as two sizes of DNNs: 2048 hidden layer nodes and 4096 nodes. Furthermore,...
It is well known that recognizers personalized to each user are much more effective than user-independent recognizers. With the popularity of smartphones today, although it is not difficult to collect a large set of audio data for each user, it is difficult to transcribe it. However, it is now possible to automatically discover acoustic tokens from unlabeled personal data in an unsupervised way. We...
This paper advances the design of CTC-based all-neural (or end-to-end) speech recognizers. We propose a novel symbol inventory, and a novel iterated-CTC method in which a second system is used to transform a noisy initial output into a cleaner version. We present a number of stabilization and initialization methods we have found useful in training these networks. We evaluate our system on the commonly...
One of the difficulties in sung speech recognition is the small distance in an acoustic space between phonemes in sung speech. Therefore we considered clustering the speech based on a pitch (fundamental frequency F0) and creating a larger distance between the phonemes. In addition, we considered a two-stage training method of DNN-HMM: the first stage is trained by using conventional acoustic features...
This paper investigates the application of unsupervised acoustic unit discovery for topic identification (topic ID) of spoken audio documents. The acoustic unit discovery method is based on a non-parametric Bayesian phone-loop model that segments a speech utterance into phone-like categories. The discovered phone-like (acoustic) units are further fed into the conventional topic ID framework. Using...
Recent works have shown that hierarchical models lead to significant improvement in human activity recognition, which can not only enhance descriptive capability, but also improve discriminative power. However, most existing methods exploit just one of the two advantages. In this paper, a new hierarchical spatio-temporal model (HSTM) is proposed to integrate feature learning into two-layer hierarchical...
In this paper we describe the 2016 BBN conversational telephone speech keyword spotting system; the culmination of four years of research and development under the IARPA Babel program. The system was constructed in response to the NIST Open Keyword Search (OpenKWS) evaluation of 2016. We present our technological breakthroughs in building top-performing keyword spotting processing systems for new...
This paper investigates the framework of encoder-decoder with attention for sequence labelling based spoken language understanding. We introduce Bidirectional Long Short Term Memory - Long Short Term Memory networks (BLSTM-LSTM) as the encoder-decoder model to fully utilize the power of deep learning. In the sequence labelling task, the input and output sequences are aligned word by word, while the...
Automatic drum transcription methods aim at extracting a symbolic representation of notes played by a drum kit in audio recordings. For automatic music analysis, this task is of particular interest as such a transcript can be used to extract high level information about the piece, e.g., tempo, downbeat positions, meter, and genre cues. In this work, an approach to transcribe drums from polyphonic...
Convolutional Neural Networks (CNNs) have proven very effective in image classification and show promise for audio. We use various CNN architectures to classify the soundtracks of a dataset of 70M training videos (5.24 million hours) with 30,871 video-level labels. We examine fully connected Deep Neural Networks (DNNs), AlexNet [1], VGG [2], Inception [3], and ResNet [4]. We investigate varying the...
Audio-visual speech recognition is a promising approach to tackling the problem of reduced recognition rates under adverse acoustic conditions. However, finding an optimal mechanism for combining multi-modal information remains a challenging task. Various methods are applicable for integrating acoustic and visual information in Gaussian-mixture-model-based speech recognition, e.g., via dynamic stream...
In this paper, a blind bandwidth extension algorithm for music signals has been proposed. This method applies the K-means algorithm to firstly cluster audio data in the feature space, and constructs multiple envelope predictors for each cluster accordingly using Support Vector Regression (SVR). A set of well-established audio features for Music Information Retrieval (MIR) has been used to characterize...
Conventional deep neural networks (DNN) for speech acoustic modeling rely on Gaussian mixture models (GMM) and hidden Markov model (HMM) to obtain binary class labels as the targets for DNN training. Subword classes in speech recognition systems correspond to context-dependent tied states or senones. The present work addresses some limitations of GMM-HMM senone alignments for DNN training. We hypothesize...
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.