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.
This paper presents a novel method for voicing information estimation of individual frequency-regions of speech spectra and its employment in a text-independent speaker identification system. The voicing information is incorporated to the system in a form of a mask in a marginalization-based missing-feature model. Experiments were performed on speech data from the TIMIT database corrupted by stationary...
Speech recognition systems generally use delta and delta-delta (velocity and acceleration) coefficients to characterise the dynamics apparent in frame-based representations of speech. These coefficients can be thought of as the errors of simple predictors. This paper describes the use of error coefficients derived from more advanced (and accurate) forms of prediction and interpolation. Both overall...
This paper presents a method for phone-dependent weighting within phonotactic models in automatic language identification. Based on statistical analysis of the phonetic-recognizer behaviour, a phone confidence measure is derived and used to weight the bigram probabilities during testing. The confidence corresponds to the expected decoding stability of individual phones. The proposed method was shown...
Speaker identification (SID) in cochannel speech, where two speakers are talking simultaneously over a single recording channel, is a challenging problem. Previous studies address this problem in the anechoic environment under the Gaussian mixture model (GMM) framework. On the other hand, cochannel SID in reverberant conditions has not been addressed. This paper studies cochannel SID in both anechoic...
For automatic speech recognition (ASR) of lectures, texts of presentation slides are expected to be useful for adapting a language model, while slide texts are not always available in a machine-readable form. In this paper, we propose a language model adaptation framework that uses character recognition results of slide images in a lecture video. Since character recognition results contain many errors,...
We propose a novel approach for addressing automatic speech recognition (ASR) and natural language understanding (NLU) errors in an interactive spoken dialog system using targeted clarification (TC). TC applies when a spoken utterance is partially recognized by focusing a clarification question on the misrecognized part of the utterance. A key component of TC is accurate detection of localized ASR...
A group of junior and senior researchers gathered as a part of the 2014 Frederick Jelinek Memorial Workshop in Prague to address the problem of predicting the accuracy of a nonlinear Deep Neural Network probability estimator for unknown data in a different application domain from the domain in which the estimator was trained. The paper describes the problem and summarizes approaches that were taken...
We propose the prediction-adaptation-correction RNN (PAC-RNN), in which a correction DNN estimates the state posterior probability based on both the current frame and the prediction made on the past frames by a prediction DNN. The result from the main DNN is fed back to the prediction DNN to make better predictions for the future frames. In the PAC-RNN, we can consider that, given the new, current...
The recognition of contact names in mobile-device voice commands is a challenging problem. Some of the difficulties include potentially infinite vocabularies, low probability of contact tokens in the language model (LM), increased false triggering of contact voice commands when none are spoken, and very large and noisy contact name lists. In this paper we suggest solutions for each of these difficulties.
Hidden Markov Models (HMMs) are one of the most important techniques to model and classify sequential data. Maximum Likelihood (ML) and (parametric and non-parametric) Bayesian estimation of the HMM parameters suffers from local maxima and in massive datasets they can be specially time consuming. In this paper, we extend the spectral learning of HMMs, a moment matching learning technique free from...
Traditional sound event recognition methods based on informative front end features such as MFCC, with back end sequencing methods such as HMM, tend to perform poorly in the presence of interfering acoustic noise. Since noise corruption may be unavoidable in practical situations, it is important to develop more robust features and classifiers. Recent advances in this field use powerful machine learning...
The robustness of speech recognizers towards noise can be increased by normalizing the statistical moments of the Mel-frequency cepstral coefficients (MFCCs), e. g. by using cepstral mean normalization (CMN) or cepstral mean and variance normalization (CMVN). The necessary statistics are estimated over a long time window and often, a complete utterance is chosen. Consequently, changes in the background...
In this paper we explore one of the key aspects in building an emotion recognition system: generating suitable feature representations. We generate feature representations from both acoustic and lexical levels. At the acoustic level, we first extract low-level features such as intensity, F0, jitter, shimmer and spectral contours etc. We then generate different acoustic feature representations based...
For many years, filterbanks have been widely used as one step of frontend feature extraction for Automatic Speech Recognition (ASR). In this paper, we propose a unified framework for ASR frontends, by first moving the nonlinear amplitude scaling, and then combining the filterbank weights with the cosine basis vectors. As part of this framework, we also show that the delta terms used to encode feature...
Recurrent neural networks (RNNs) have recently been applied as the classifiers for sequential labeling problems. In this paper, deep bidirectional RNNs (DBRNNs) are applied for the first time to error detection in automatic speech recognition (ASR), which is a sequential labeling problem. We investigate three types of ASR error detection tasks, i.e. confidence estimation, out-of-vocabulary word detection...
Motivated by the recent progresses in the use of deep learning techniques for acoustic speech recognition, we present in this paper a visual deep bottleneck feature (DBNF) learning scheme using a stacked auto-encoder combined with other techniques. Experimental results show that our proposed deep feature learning scheme yields approximately 24% relative improvement for visual speech accuracy. To the...
The presence of Lombard Effect in speech is proven to have severe effects on the performance of speech systems, especially speaker recognition. Varying kinds of Lombard speech are produced by speakers under influence of varying noise types [1]. This study proposes a high-accuracy classifier using deep neural networks for detecting various kinds of Lombard speech against neutral speech, independent...
This paper presents a novel interactive method for recognizing handwritten words, using the inertial sensor data available on smart watches. The goal is to allow the user to write with a finger, and use the smart watch sensor signals to infer what the user has written. Past work has exploited the similarity of handwriting recognition to speech recognition in order to deploy HMM based methods. In contrast...
Due to a large number of parameters in deep neural networks (DNNs), it is challenging to design a small-footprint DNN-based speech recognition system while maintaining a high recognition performance. Even with a singular value matrix decomposition (SVD) method and scalar quantization, the DNN model is still too large to be deployed on many mobile devices. Common practices like reducing the number...
Traditional speech recognition systems use Gaussian mixture models to obtain the likelihoods of individual phonemes, which are then used as state emission probabilities in hidden Markov models representing the words. In hybrid systems, the Gaussian mixtures are replaced by more discriminant classifiers, leading to an improved performance. Most of the time the classifiers used in such systems are neural...
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.