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 data selection to maximize acoustic diversity through Gaussian component indexed N-grams; (2) Keywordaware language modeling; (3) Subword modeling of morphemes and homophones.

In this paper, we use image processing techniques on the speech spectrogram to perform speech phoneme segmentation. The proposed method relies solely on visual cues on the spectrogram, without the need for language-specific training data. The results are evaluated on the TIMIT corpus, and compared to other unsupervised speech segmentation techniques, with comparable results obtained. We also fuse the results with those obtained by hidden Markov models (HMM) and HMM-based forced alignment to investigate if image features can provide an additional feature representation for speech processing tasks. With the fusion, up to 10% absolute improvement in segmentation accuracy over the HMM baselines can be obtained. Results are promising and suggests a strong potential for image-based features applying to speech processing.

In this paper, we propose a partial sequence matching based symbolic search (SS) method for the task of language independent query-by-example spoken term detection. One main drawback of conventional SS approach is the high miss rate for long queries. This is due to high variations in symbol representation of query and search audios, especially in language independent scenario. The successful matching of a query with its instances in search audio becomes exponentially more difficult as the query grows longer. To reduce miss rate, we propose a partial matching strategy, in which all partial phone sequences of a query are used to search for query instances. The partial matching is also suitable for real life applications where exact match is usually not necessary and word prefix, suffix, and order should not affect the search result. When applied to the QUESST 2014 task, results show the partial matching of phone sequences is able to reduce miss rate of long queries significantly compared with conventional full matching method. In addition, for the most challenging inexact matching queries (type 3), it also shows clear advantage over DTW-based methods.

Origamic architecture (OA) is a form of papercraft that involves cutting and folding a single sheet of paper to produce a 3D pop-up, and is commonly used to depict architectural structures. Because of the strict geometric and physical constraints, OA design requires considerable skill and effort. In this paper, we present a method to automatically generate an OA design that closely depicts an input 3D model. Our algorithm is guided by a novel set of geometric conditions to guarantee the foldability and stability of the generated pop-ups. The generality of the conditions allows our algorithm to generate valid pop-up structures that are previously not accounted for by other algorithms. Our method takes a novel image-domain approach to convert the input model to an OA design. It performs surface segmentation of the input model in the image domain, and carefully represents each surface with a set of parallel patches. Patches are then modified to make the entire structure foldable and stable. Visual and quantitative comparisons of results have shown our algorithm to be significantly better than the existing methods in the preservation of contours, surfaces, and volume. The designs have also been shown to more closely resemble those created by real artists.