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.
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,...
It has been shown that sequence-discriminative training can improve the performance for large vocabulary continuous speech recognition. Our main contribution is a novel method for reducing the computation time of any sort of sequence training while only slightly decreasing the overall performance. The method allows to parallelize the forward propagation through the network, the loss and loss gradient...
When using connectionist temporal classification (CTC) based acoustic models (AMs) for large vocabulary continuous speech recognition (LVCSR), most previous studies have used a naive interpolation of the CTC-AM score and an additional language model score, although there is no theoretical justification for such an approach. On the other hand, we recently proposed a theoretically more sound decoding...
In this work we study variance in the results of neural network training on a wide variety of configurations in automatic speech recognition. Although this variance itself is well known, this is, to the best of our knowledge, the first paper that performs an extensive empirical study on its effects in speech recognition. We view training as sampling from a distribution and show that these distributions...
Proxy-word based out of vocabulary (OOV) keyword search has been proven to be quite effective in keyword search. In proxy-word based OOV keyword search, each OOV keyword is assigned several proxies and detections of the proxies are regarded as detections of the OOV keywords. However, the confidence scores of these detections are still those of the proxies from lattices. To obtain a better confidence...
Automatic speech recognition systems can benefit from cues in user voice such as hyperarticulation. Traditional approaches typically attempt to define and detect an absolute state of hyperarticulation, which is very difficult, especially on short voice queries. We present a novel approach for hyperarticulation detection using pairwise comparisons and demonstrate its application in a real-world speech...
In this paper, we introduce a multimodal speech recognition scenario, in which an image provides contextual information for a spoken caption to be decoded. We investigate a lattice rescoring algorithm that integrates information from the image at two different points: the image is used to augment the language model with the most likely words, and to rescore the top hypotheses using a word-level RNN...
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...
We present detailed analysis of phoneme recognition performance of a context dependent tied-state triphone Gaussian Mixture Model Hidden Markov Model (CD-GMM-HMM) acoustic model (state-of-the-art large acoustic model (AM)) and a four hidden layer context dependent Deep Neural Network (CD-DNN-HMM) AM on the WSJ speech corpus. Using a bigram phoneme language model, phoneme recognition experiments are...
This paper presents a two-pass framework of mispronunciation detection and diagnosis (MD&D) — detection followed by diagnosis, without the need of explicit error pattern modeling, so that the main efforts can be devoted to improving acoustic modeling by discriminative training (or by applying alternative models like neural nets). The framework instantiates a set of anti-phones and a filler model...
Spoken language translation (SLT) combines automatic speech recognition (ASR) and machine translation (MT). During the decoding stage, the best hypothesis produced by the ASR system may not be the best input candidate to the MT system, but making use of multiple sub-optimal ASR results in SLT has been shown to be too complex computationally. This paper presents a method to rescore the k-best ASR output...
This paper investigates a weighted finite state transducer (WFST) based syllable decoding and transduction method for keyword search (KWS), and compares it with sub-word search and phone confusion methods in detail. Acoustic context dependent phone models are trained from word forced alignments and then used for syllable decoding and lattice generation. Out-of-vocabulary (OOV) keyword pronunciations...
This paper proposes a method to train Weighted Finite State Transducer (WFST) based structural classifiers using deep neural network (DNN) acoustic features and recurrent neural network (RNN) language features for speech recognition. Structural classification is an effective approach to achieve highly accurate recognition of structured data in which the classifier is optimized to maximize the discriminative...
In this paper we describe approaches to building our recent Malay broadcast news audio retrieval system. This system contains speech-to-text and keyword search subsystems. The speech-to-text system is built aiming at two folds: hybrid vocabulary recognition to tackle out-of-vocabulary keyword search issue and diversified acoustic modeling for effective system combination in keyword searching afterwards...
In phonotactic spoken language recognition systems, acoustic model adaptation prior to phone lattice decoding has been adopted to deal with the mismatch between training and test conditions. Moreover, combining diversified phonotactic features is commonly used. These motivate us to have an in-depth investigation of combining diversified phonotactic features from diversely adapted acoustic models....
We present our work on semi-supervised learning of discriminative language models where the negative examples for sentences in a text corpus are generated using confusion models for Turkish at various granularities, specifically, word, sub-word, syllable and phone levels. We experiment with different language models and various sampling strategies to select competing hypotheses for training with a...
This paper introduces a discriminative extension to whole-word point process modeling techniques. Meant to circumvent the strong independence assumptions of their generative predecessors, discriminative point process models (DPPM) are trained to distinguish the composite temporal patterns of phonetic events produced for a given word from those of its impostors. Using correct and incorrect word hypotheses...
Unsupervised acoustic model training has been successfully used to improve the performance of automatic speech recognition systems when only a small amount of manually transcribed data is available for the target domain. The most common approach is use automatic transcriptions to guide acoustic model estimation. However, since the best recognition hypotheses are known to contain errors, we propose...
In this paper, we extend our previous study on discriminative training using non-uniform criteria for speech recognition. The work will put emphasis on how the acoustic modeling interacts with the risk at a higher level, which is more relevant to the most used evaluation measures, e.g., word error rate(WER). To be specific, the non-uniform error cost is first derived at the word level to minimize...
We investigate the problem of adapting a recognition system with multiple acoustic models to a new domain in unsupervised mode. We compare maximum likelihood and discriminative approaches for unsupervised domain adaptation. Different adaptation data selection methods and adaptation strategies are investigated, using a baseline meeting recognition system and adaptation data from a congressional committee...
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.