Helen M. Meng

Learn More
We have developed a technique for automatic transliteration of named entities for English-Chinese cross-language spoken document retrieval (CL-SDR). Our retrieval system integrates machine translation, speech recognition and information retrieval technologies. An English news story forms a textual query that is automatically translated into Chinese words,(More)
This paper describes a new system for speech analysis, ANGIE, which characterizes word substructure in terms of a trainable grammar. ANGIE capture morpho-phonemic and phonological phenomena through a hierarchical framework. The terminal categories can be alternately letters or phone units, yielding a reversible letter-tosound/sound-to-letter system. In(More)
This paper describes theMandarin–English Information (MEI) project, wherewe investigated the problemof cross-language spoken document retrieval (CL-SDR), and developed one of the first English–Chinese CL-SDR systems.Our systemaccepts an entireEnglish news story (text) asquery, and retrieves relevantChinese broadcast news stories (audio) from the document(More)
Deep belief network (DBN) has been shown to be a good generative model in tasks such as hand-written digit image generation. Previous work on DBN in the speech community mainly focuses on using the generatively pre-trained DBN to initialize a discriminative model for better acoustic modeling in speech recognition (SR). To fully utilize its generative(More)
Hidden Markov models (HMMs) and Gaussian mixture models (GMMs) are the two most common types of acoustic models used in statistical parametric approaches for generating low-level speech waveforms from high-level symbolic inputs via intermediate acoustic feature sequences. However, these models have their limitations in representing complex, nonlinear(More)
This paper describes the use of Belief Networks for mixedinitiative dialog modeling within the context of the CU FOREX system [1]. CU FOREX is a bilingual hotline for real-time foreign exchange inquiries. Presently, it supports two separate interaction modalities: a direct dialog (DD) interaction, which is systeminitiated for novice users; as well as(More)
The tasks in fine-grained opinion mining can be regarded as either a token-level sequence labeling problem or as a semantic compositional task. We propose a general class of discriminative models based on recurrent neural networks (RNNs) and word embeddings that can be successfully applied to such tasks without any taskspecific feature engineering effort.(More)
This paper investigates the use of Deep Bidirectional Long Short-Term Memory based Recurrent Neural Networks (DBLSTM-RNNs) for voice conversion. Temporal correlations across speech frames are not directly modeled in frame-based methods using conventional Deep Neural Networks (DNNs), which results in a limited quality of the converted speech. To improve the(More)
ÐThis paper describes a methodology for semiautomatic grammar induction from unannotated corpora of information-seeking queries in a restricted domain. The grammar contains both semantic and syntactic structures, which are conducive to (spoken) natural language understanding. Our work aims to ameliorate the reliance of grammar development on expert(More)