We describe a system which supports English text queries searching for Mandarin Chinese spoken documents.

r exact morphology. For IR purposes a document might be adequately modeled with a vector of indexing features that is a histogram of word stems. A Spoken Document Retrieval (SDR) system requires language representations suited for speech recognition as well as for IR. For additional general information concerning SDR refer to [4]. The first step in the design of any language model involves the choice of what units to use as fundamental features. For LVCSR language models these features are the underlying inventory of base units over which the statistical model is defined. For IR language models these features are the indexing features that will be used to compute the relevance of the document to the user query. This extended abstract explores the base units of language models as a point of contact between language models for LVCSR and for IR, and tries to shed light how SDR systems can be built with an optimal interface between speech recognition and IR. The first section sketches dist

Cross-language spoken document retrieval (CL-SDR) is the technology that facilitates automatic retrieval of relevant information from a collection of spoken documents in a language that is different from that used in the queries. Information sources that are in different languages can then be retrieved automatically with CL-SDR, and the number of searchable information sources will increase significantly. The HMM-based retrieval model is a probabilistic formulation for the retrieval problem. Extensions to this retrieval model can be made by taking advantage of its probabilistic nature. Specifically, we have incorporated the translation component to make it possible to perform cross-language information retrieval (CLIR). In addition, this HMM-based CLIR retrieval model is also extended for retrieval at subword scales. In this work the extended HMM-based retrieval model has been applied to an English-Mandarin CL-SDR task, which is to search the Mandarin spoken document collection with English queries at word and subword scales. Retrieval results obtained from these indexing scales are then fused for multi-scale CL-SDR. Experimental results demonstrate that improvement in CL-SDR retrieval performance can be achieved by fusion of word and subword scales.

This paper presents a multi-scale retrieval approach in MEI (Mandarin-English Information), an English-Chinese crosslingual spoken document retrieval (CL-SDR) system. It accepts an entire English news story (from newspaper text) as the input query, and automatically retrieves "relevant " Mandarin news stories (from broadcast audio). This allows the user to search for personally relevant content across the language and media barriers – a cross-lingual and cross-media retrieval task. MEI advocates a multi-scale paradigm for the retrieval task. Multiscale refers to the use of both words and subwords (Chinese characters and syllables) for retrieval. Words offer lexical knowledge to enhance precision, and subwords can potentially alleviate some prevailing problems in CL-SDR, e.g. open vocabularies in translation and recognition, out-of-vocabulary words in audio indexing, and ambiguities in Chinese homophones and word tokenizaiton. We present techniques for word-subword fusion, which improved retrieval performance in our experiments with the Topic Detection and Tracking collection. 1.

This paper presents the application of a multi-scale paradigm to Chinese spoken document retrieval (SDR) for improving retrieval performance. Multi-scale refers to the use of both words and subwords for retrieval. Words are basic units in a language that carry lexical meaning and subword units (such as phonemes, syllables or characters) are building components for words. Retrieval using subword indexing units is found to perform better than words because of the robustness of subword units to out-of-vocabulary (OOV) words during speech recognition and ambiguities in word segmentation. Experimental results have demonstrated that subword bigrams can bring improvement in retrieval performance over words (~9.56%). Application of multi-scale fusion to SDR aims at combining the lexical information of words and the robustness of subwords. This work presents the first detailed investigation for a Cantonese broadcast news retrieval task using two different multi-scale fusion approaches: pre-retrieval fusion and post-retrieval fusion. Multi-scale retrieval using both words and syllable bigrams achieve improvement in retrieval performance (~1.90%) over retrieval on the composite scales.