Audio-visual TED corpus

—This paper presents the main improvements brought recently to the SpeeD automatic speech recognition system. Several aspects, such as speech and text resources acquisition, noise-robust speech features and feature transforms are discussed. All the updates in our ASR system are accompanied by experimental results illustrating significant improvements: between 30% and 35% relative WER reductions for various case studies (read/spontaneous speech, noisy/clean speech). In the last part of the paper, our ASR system is also compared with Google’s ASR system and a brief analysis of the results is presented. Keywords -ASR; LVCSR; noise-robust speech recognition; PNCC; LDA. I. I NTRODUCTION Large vocabulary continuous speech recognition (LVCSR) is still an unsolved topic for many languages. The reasons for this are (i) there is a lack of acoustic and linguistic resources needed for development (it is the case of so-called under-resourced languages) and (ii) the scientific research community is not stimulated by any national or international evaluation campaigns (as opposed to languages such as English, French or Chinese). The Romanian language is affected by both the aforementioned problems. In this context, the development of speech and language resources for automatic speech recognition (ASR) is a critical issue that must be addressed to push forward the research in this direction and create LVCSR systems comparable to those available for other languages. This is one of the main goals of the Speech and Dialogue (SpeeD) research group

For accurate and fast detection of facial landmarks, we propose a new facial landmark detection method. Previous facial landmark detection models generally perform a face detection step before landmark detection. This greatly affects landmark detection performance depending on which face detection model is used. Therefore, we propose a model that can simultaneously detect a face region and a landmark without performing the face detection step before landmark detection. The proposed single-shot detection model is based on the framework of YOLOv3, a one-stage object detection method, and the loss function and structure are altered to learn faces and landmarks at the same time. In addition, EfficientNet-B0 was utilized as the backbone network to increase processing speed and accuracy. The learned database used 300W-LP with 64 facial landmarks. The average normalized error of the proposed model was 2.32 pixels. The processing time per frame was about 15 milliseconds, and the average precision of face detection was about 99%. As a result of the evaluation, it was confirmed that the single-shot detection model has better performance and speed than the previous methods. In addition, as a result of using the COFW database, which has 29 landmarks instead of 64 to verify the proposed method, the average normalization error was 2.56 pixels, which was also confirmed to show promising performance.

Widespread use of large‐vocabulary continuous speech recognition systems has recently occurred, encouraging the application of speech recognition techniques to various problems. One of the factors that adversely affect the performance of speech recognition systems is a mismatch between the acoustic properties of the speech of the system user and the acoustic model. The speech of young or middle‐aged adults is generally used in constructing the acoustic model. Thus, a mismatch occurs between the model and the acoustic properties of the speech of the elderly, which may degrade the recognition rate. In this study, a large‐scale elderly speech database (200 sentences ×301 subjects) is used to train the acoustic model, and the resulting elderly acoustic model is evaluated by using a large‐vocabulary continuous speech recognition system. In the experiments, the word recognition rate was improved by 3 to 5% compared to the recognition results of an acoustic model trained by young or middle‐aged adult speech, namely, by the JNAS speech database (150 sentences ×260 subjects, average 28.6 years). It is also verified experimentally that the recognition rate is further improved in speaker adaptation to elderly speech by making use of an acoustic model trained by elderly speech. © 2004 Wiley Periodicals, Inc. Electron Comm Jpn Pt 2, 87(7): 49–57, 2004; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/ecjb.20101

State-of-the-art large vocabulary continuous speech recognition (LVCSR) systems often combine outputs from multiple sub-systems that may even be developed at different sites. Cross system adaptation, in which model adaptation is performed using the outputs from another sub-system, can be used as an alternative to hypothesis level combination schemes such as ROVER. Normally cross adaptation is only performed on the acoustic models. However, there are many other levels in LVCSR systems' modelling hierarchy where complimentary features may be exploited, for example, the sub-word and the word level, to further improve cross adaptation based system combination. It is thus interesting to also cross adapt language models (LMs) to capture these additional useful features. In this paper cross adaptation is applied to three forms of language models, a multi-level LM that models both syllable and word sequences, a word level neural network LM, and the linear combination of the two. Significant error rate reductions of 4.0-7.1% relative were obtained over ROVER and acoustic model only cross adaptation when combining a range of Chinese LVCSR sub-systems used in the 2010 and 2011 DARPA GALE evaluations.

The diachronic nature of broadcast news data leads to the problem of out-of-vocabulary (OOV) words in large vocabulary continuous speech recognition (LVCSR) systems. Analysis of OOV words reveals that a majority of them are proper names (PNs). However, PNs are important for automatic indexing of audio–video content and for obtaining reliable automatic transcriptions. In this paper, we focus on the problem of OOV PNs in diachronic audio documents. To enable the recovery of the PNs missed by the LVCSR system, relevant OOV PNs are retrieved by exploiting the semantic context of the LVCSR transcriptions. For retrieval of OOV PNs, we explore topic and semantic context derived from latent Dirichlet allocation (LDA) topic models, continuous word vector representations and the neural bag-of-words (NBOW) model which is capable of learning task specific word and context representations. We propose a neural bag-of-weighted words (NBOW2) model which learns to assign higher weights to words that are important for retrieval of an OOV PN. With experiments on French broadcast news videos, we show that the NBOW and NBOW2 models outperform the methods based on raw embeddings from LDA and Skip-gram models. Combining the NBOW and NBOW2 models gives a faster convergence during training. Second pass speech recognition experiments, in which the LVCSR vocabulary and language model are updated with the retrieved OOV PNs, demonstrate the effectiveness of the proposed context models.

We like to conversate with other people using both sounds and visuals, as our perception of speech is bimodal. Essentially echoing the same speech structure, we manage to integrate the two modalities and often understand the message better than with the eyes closed. In this work we would like to learn more about the visual nature of speech, coined lip-reading, and to make use of it towards better automatic speech recognition systems. Recent developments in the Machine Learning area, together with the release of suitable audio-visual datasets aimed at large vocabulary continuous speech recognition, have led to a renewal of the lip-reading topic, and allow us to address the recurring question of how to better integrate visual and acoustic speech.

This paper deals with the use of a stochastic context‐free grammar (SCFG) for large vocabulary continuous speech recognition; in particular, an SCFG with phrase‐level dependency rules is built. Unlike n‐gram models, the SCFG can describe not only local constraints but also global constraints pertaining to the sentence as a whole, thus making possible language models with great expressive power. However, the inside‐outside algorithm must be used for estimation of the SCFG parameters, which involves a great amount of calculation, proportional to the third power of the number of nonterminal symbols and of the input string length. Hence, due to problems in dealing with extensive text corpora, the SCFG has hardly been applied as a language model for very large vocabulary continuous speech recognition. The proposed phrase‐level dependency SCFG allows a significant reduction of the computational load. In experiments with the EDR corpus, the proposed method proved effective. In experiments with the Mainichi corpus, a large‐scale phrase‐level dependency SCFG was built for a very large vocabulary continuous speech recognition system. Speech recognition tests with a vocabulary of about 5000 words showed that the proposed method could not compare with the trigram model in performance; however, when it was used in combination with a trigram model, the error rate was reduced by 14% compared to the trigram model alone. © 2002 Wiley Periodicals, Inc. Syst Comp Jpn, 33(13): 48–59, 2002; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/scj.1172

In this paper, we present a novel method to regulate lexical connections among morpheme-based pronunciation lexicons for Korean large vocabulary continuous speech recognition (LVCSR) systems. A pronunciation dictionary plays an important role in subword-based LVCSR in that pronunciation variations such as coarticulation will deteriorate the performance of an LVCSR system if it is not well accounted for. In general, pronunciation variations are modeled by applying phonological variations with all possible phonemic contexts. In order to achieve high recognition performance, current speech recognition systems impose constraints among lexicons using both morphological and phonetic knowledge. This paper suggests a method both to refine pronunciation variations according to cross-morpheme phonetic information and to regulate the connections between pronunciation variants. This method effectively excludes improper connections between pronunciation lexicons, and thus the proposed method gave a 27% reduction in word error rate over the recognizer with conventional lexicons relatively.

Facial landmark detection is an important yet challenging task for real-world\ncomputer vision applications. This paper proposes an effective and robust\napproach for facial landmark detection by combining data- and model-driven\nmethods. Firstly, a Fully Convolutional Network (FCN) is trained to compute\nresponse maps of all facial landmark points. Such a data-driven method could\nmake full use of holistic information in a facial image for global estimation\nof facial landmarks. After that, the maximum points in the response maps are\nfitted with a pre-trained Point Distribution Model (PDM) to generate the\ninitial facial shape. This model-driven method is able to correct the\ninaccurate locations of outliers by considering the shape prior information.\nFinally, a weighted version of Regularized Landmark Mean-Shift (RLMS) is\nemployed to fine-tune the facial shape iteratively. This\nEstimation-Correction-Tuning process perfectly combines the advantages of the\nglobal robustness of data-driven method (FCN), outlier correction capability of\nmodel-driven method (PDM) and non-parametric optimization of RLMS. Results of\nextensive experiments demonstrate that our approach achieves state-of-the-art\nperformances on challenging datasets including 300W, AFLW, AFW and COFW. The\nproposed method is able to produce satisfying detection results on face images\nwith exaggerated expressions, large head poses, and partial occlusions.\n

Cascade regression framework has been shown to be effective for facial landmark detection. It starts from an initial face shape and gradually predicts the face shape update from the local appearance features to generate the facial landmark locations in the next iteration until convergence. In this paper, we improve upon the cascade regression framework and propose the Constrained Joint Cascade Regression Framework (CJCRF) for simultaneous facial action unit recognition and facial landmark detection, which are two related face analysis tasks, but are seldomly exploited together. In particular, we first learn the relationships among facial action units and face shapes as a constraint. Then, in the proposed constrained joint cascade regression framework, with the help from the constraint, we iteratively update the facial landmark locations and the action unit activation probabilities until convergence. Experimental results demonstrate that the intertwined relationships of facial action units and face shapes boost the performances of both facial action unit recognition and facial landmark detection. The experimental results also demonstrate the effectiveness of the proposed method comparing to the state-of-the-art works.

This paper reports the development of a multi-genre Urdu Broadcast (BC) corpus and a Large Vocabulary Continuous Speech Recognition (LVCSR) system. BC speech corpus of 98 hours from 453 speakers is collected and annotated. For acoustic modeling, Time-delay Neural Network (TDNN) is developed with prior Gaussian Mixture Model-Hidden Markov Model (GMM-HMM) training and alignments. For the language model, 3-gram, 4-gram and Recurrent Neural Network (RNN) based models are developed on a text corpus of 188 million words. The developed models are tested on 4.3 hours of unseen BC multi-genre speech dataset and the best Word Error Rate (WER) 18.59% is achieved using RNN based Language Model (LM). Moreover, a detailed word error analysis is carried out to compare the errors made by humans and the Automatic Speech Recognition (ASR) System. The results showed a similar behavior of word misrecognitions by both humans and ASR.

In this paper, we propose a lexicon optimization method based on confusability measure (CM) in order to reduce the decoding time for a large vo- cabulary continuous speech recognition (LVCSR) system. When lexicon is built or expanded for unseen words by using grapheme-to-phoneme (G2P) conver- sion, the lexicon size increases since G2P is generally realized by 1-to-N-best mapping. Thus, the proposed method prunes the confusable words in the lexi- con by a CM that is defined a linguistic distance between two phonemic se- quences. It is demonstrated from LVCSR experiments that the proposed lexicon optimization method achieves a relative real-time factor reduction of 23.13% on a task on the Wall Street Journal, compared to the 1-to-4-best G2P converted lexicon approach.

Multivariate Gaussian based speech compensation or mapping has been developed to reduce the mismatch between training and deployment conditions for robust speech recognition. The acoustic mapping procedure can be formulated as a feature space adaptation where a noisy input signal is transformed by a multivariate Gaussian network. We propose a novel algorithm to update the network parameters based on minimizing the Kullback-Leibler distance between the core recognizer's acoustic model and transformed features. It is designed to achieve optimal overall system performance rather than MMSE on a specific feature domain. An online stochastic gradient descent learning rule is derived. We evaluate the performance of the new algorithm using a JRTk broadcast news system on a distance-talking speech corpus and compare its performance with that of previous MMSE based approaches. The experiments show the KL based approach is more effective for a large vocabulary continuous speech recognition (LVCSR) system.

This paper presents a deep neural network (DNN) based large vocabulary continuous speech recognition (LVCSR) system for Serbian, developed using the open-source Kaldi speech recognition toolkit. The DNNs are initialized using stacked restricted Boltzmann machines (RBMs) and trained using cross-entropy as the objective function and the standard error backpropagation procedure in order to provide posterior probability estimates for the hidden Markov model (HMM) states. Emission densities of HMM states are represented as Gaussian mixture models (GMMs). The recipes were modified based on the particularities of the Serbian language in order to achieve the optimal results. A corpus of approximately 90 hours of speech (21000 utterances) is used for the training. The performances are compared for two different sets of utterances between the baseline GMM-HMM algorithm and various DNN settings.KeywordsKaldi speech recognition toolkitContinuous speech recognitionDeep neural networksSerbian

This paper introduces extended weighted linear prediction (XLP) to noise robust short-time spectrum analysis in the feature extraction process of a speech recognition system. XLP is a generalization of standard linear prediction (LP) and temporally weighted linear prediction (WLP) which have already been applied to noise robust speech recognition with good results. With XLP, higher controllability to the temporal weighting of different parts of the noisy speech is gained by taking the lags of the signal into account in prediction. Here, the performance of XLP is put up against WLP and conventional spectrum analysis methods FFT and LP on a large vocabulary continuous speech recognition (LVCSR) scheme using real world noisy data containing additive and convolutive noise. The results show improvements over the reference methods in several cases. Index Terms: linear prediction, temporal weighting, noise robust, speech recognition