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.
Training a bottleneck feature (BNF) extractor with multilingual data has been common in low resource keyword search. In a low resource application, the amount of transcribed target language data is limited while there are usually plenty of multilingual data. In this paper, we investigated two methods to train efficient multilingual BNF extractors for low resource keyword search. One method is to use...
In this paper, we investigate a DNN tone-based extended recognition network (ERN) approach to Mandarin tone recognition and tone mispronunciation detection. Given a toneless syllable sequence, a tone-based ERN is constructed by assigning five different tones to each toneless syllable, obtaining a fully expanded tonal syllable network. Next, Viterbi decoding is carried out on the tone-based ERN to...
This paper reviews the research approaches used in computer-assisted pronunciation training (CAPT), addresses the existing challenges, and discusses emerging trends and opportunities. To complement existing work, our analysis places more emphasis on pronunciation teaching and learning (as opposed to pronunciation assessment), prosodic error detection (as opposed to phonetic error detection), and research...
Mismatched crowdsourcing is a technique to derive speech transcriptions using crowd-workers unfamiliar with the language being spoken. This technique is especially useful for under-resourced languages since it is hard to hire native transcribers. In this paper, we demonstrate that using mismatched transcription for adaptation improves performance of speech recognition under limited matched training...
This paper presents a novel method for acoustic modeling of an under-resourced language by “mapping” from acoustic models of well-resourced languages. The proposed method can be considered as a “many-to-one mapping” method where one speech unit in the target language is built as a linear combination of the source speech unit models and hence we can explicitly observe the relationship of the source...
We propose strategies for a state-of-the-art keyword search (KWS) system developed by the SINGA team in the context of the 2014 NIST Open Keyword Search Evaluation (OpenKWS14) using conversational Tamil provided by the IARPA Babel program. To tackle low-resource challenges and the rich morphological nature of Tamil, we present highlights of our current KWS system, including: (1) Submodular optimization...
In this paper, we proposed a method to realize the recently developed keyword-aware grammar for LVCSR-based keyword search using weight finite-state automata (WFSA). The approach creates a compact and deterministic grammar WFSA by inserting keyword paths to an existing n-gram WFSA. Tested on the evalpart1 data of the IARPA Babel OpenKWS13 Vietnamese and OpenKWS14 Tamil limitedlanguage pack tasks,...
This paper considers an unsupervised data selection problem for the training data of an acoustic model and the vocabulary coverage of a keyword search system in low-resource settings. We propose to use Gaussian component index based n-grams as acoustic features in a submodular function for unsupervised data selection. The submodular function provides a near-optimal solution in terms of the objective...
Neural network language models (NNLMs) have achieved very good performance in large-vocabulary continuous speech recognition (LVCSR) systems. Because decoding with NNLMs is computationally expensive, there is interest in developing methods to approximate NNLMs with simpler language models that are suitable for fast decoding. In this work, we propose an approximate method for converting a feedforward...
Shrinkage-based exponential language models, such as the recently introduced Model M, have provided significant gains over a range of tasks [1]. Training such models requires a large amount of computational resources in terms of both time and memory. In this paper, we present a distributed training algorithm for such models based on the idea of cluster expansion [2]. Cluster expansion allows us to...
Current approaches to pose estimation and tracking can be classified into two categories: generative and discriminative. While generative approaches can accurately determine human pose from image observations, they are computationally expensive due to search in the high dimensional human pose space. On the other hand, discriminative approaches do not generalize well, but are computationally efficient...
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.