Exploring the Incorporation of Acoustic Information into Term Weights for Spoken Document Retrieval
نویسنده
چکیده
Standard term weighting methods derived from experience with text collections have been used successfully in various spoken document retrieval evaluations. However, the speech recognition techniques used to index the contents of spoken documents are errorful, and these mistakes are propagated into the document index file resulting in degradation of retrieval performance. It has been suggested that, because of the uncertainty of correct recognition, term weights in spoken document retrieval might be improved by incorporating the acoustic likelihood information associated with each term by the speech recogniser. This paper examines possible techniques for incorporating acoustic likelihood starting with a theoretical analysis and an initial experimental investigation using the VMR1b collection.
منابع مشابه
Improved spoken document retrieval by exploring extra acoustic and linguistic cues
In this paper, we explored the use of various extra information to improve the performance of spoken document retrieval (SDR). From the speech recognition perspective, we incorporated the acoustic stress and word confusion information into the audio indexing. From the linguistic perspective, we applied the partof-speech information in both the audio indexing and the query representation. From t...
متن کاملSpoken Term Detection for Persian News of Islamic Republic of Iran Broadcasting
Islamic Republic of Iran Broadcasting (IRIB) as one of the biggest broadcasting organizations, produces thousands of hours of media content daily. Accordingly, the IRIBchr('39')s archive is one of the richest archives in Iran containing a huge amount of multimedia data. Monitoring this massive volume of data, and brows and retrieval of this archive is one of the key issues for this broadcasting...
متن کاملCombining Subword and State-level Dissimilarity Measures for Improved Spoken Term Detection in NTCIR-11 SpokenQuery&Doc Task
In recent years, demands for distributing or searching multimedia contents are rapidly increasing and more effective method for multimedia information retrieval is desirable. In the studies on spoken document retrieval systems, much research has been presented focusing on the task of spoken term detection (STD), which locates a given search term in a large set of spoken documents. Recently, in ...
متن کاملCombining State-level and DNN-based Acoustic Matches for Efficient Spoken Term Detection in NTCIR-12 SpokenQuery&Doc-2 Task
Recently, in spoken document retrieval task such as spoken term detection (STD), there has been increasing interest in using a spoken query. In STD systems, automatic speech recognition (ASR) frontend is often employed for its reasonable accuracy and efficiency. However, out-of-vocabulary (OOV) problem at ASR stage has a great impact on the STD performance for spoken query. In this paper, we pr...
متن کاملSpoken Term Detection Using Distance-Vector based Dissimilarity Measures and Its Evaluation on the NTCIR-10 SpokenDoc-2 Task
In recent years, demands for distributing or searching multimedia contents are rapidly increasing and more effective method for multimedia information retrieval is desirable. In the studies on spoken document retrieval systems, much research has been presented focusing on the task of spoken term detection (STD), which locates a given search term in a large set of spoken documents. One of the mo...
متن کامل