Learning on demand - course lecture distillation by information extraction and semantic structuring for spoken documents

Although network content access is primarily text-based today, almost all roles of text can be accomplished by voice. Voice-based information retrieval refers to the situation that the user query and/or the content to be retried are in form of voice. This paper tries to compare the voice-based information retrieval with the currently very successful text-based information retrieval, and identifies two major issues in which voice-based information retrieval is far behind: retrieval accuracy and user-system interaction. These two issues are reviewed, analyzed and discussed in detail. It is found that very good approaches have been proposed and very good improvements have been achieved, although there is still a very long way to go. A few successful prototype systems, among many others are presented at the end.

show abstract

“…The block diagram of the system is shown in Fig. 21 [83]. On the upper left corner the course lectures includes 3 parts: audio, video and slides.…”

Section: B a Course Lecture Browsermentioning

confidence: 99%

“…All these offer the necessary materials and scenario for the user-system interaction needed for retrieval. The user can thus enter queries to the system and learn what he needs in his own way [83].…”

Section: B a Course Lecture Browsermentioning

confidence: 99%

Voice-based information retrieval — how far are we from the text-based information retrieval ?

Lee

Pan

2009

2009 IEEE Workshop on Automatic Speech Recognition &Amp; Understanding

Self Cite

View full text Add to dashboard Cite

show abstract

“…Word-based and subword-based indexing can be further integrated to yield better performance [13], [22], [23]. Many successful applications have been demonstrated with good examples including those browsing over broadcast news [24], [25], course lectures [26], [27], historical spoken archives [28], podcasts [29], and YouTube videos [30]. However, most works in spoken content retrieval remain focused on spoken term detection (STD), for which the goal is simply returning spoken segments that include the query terms.…”

Section: Introductionmentioning

confidence: 99%

Improved Semantic Retrieval of Spoken Content by Document/Query Expansion with Random Walk Over Acoustic Similarity Graphs

Lee

2014

IEEE/ACM Trans. Audio Speech Lang. Process.

Self Cite

View full text Add to dashboard Cite

In a text context, document/query expansion has proven very useful in retrieving objects semantically related to the query. However, when applying text-based techniques on spoken content, the inevitable recognition errors seriously degrade performance even when the retrieval process is performed over lattices. We propose the estimation of more accurate term distributions (or unigram language models) for the spoken documents by acoustic similarity graphs. In this approach, a graph is constructed for each term describing the acoustic similarity among all signal regions hypothesized to be the considered term. Score propagation based on a random walk over the graph offers more reliable scores of the term hypotheses, which in turn yield more accurate term distributions (or unigram language models). This approach was applied with the language modeling retrieval approach, including using document expansion based on latent topic analysis and query expansion with a query-regularized mixture model. We extend these approaches from words to subword n-grams, and the query expansion from document-level to utterance-level and from term-based to topic-based. Experiments performed on Mandarin broadcast news showed improved performance under almost all tested conditions. Index Terms-Document expansion, latent semantic analysis, query expansion, random walk, spoken content retrieval.

show abstract

“…Word-based and subword-based indexing can be further properly integrated to yield better performance [11], [21], [22]. Many successful applications have been demonstrated with good examples including those browsing over broadcast news [23], course lectures [24], [25], podcasts [26], YouTube videos [27], etc.…”

Section: Introductionmentioning

confidence: 99%

Enhanced Spoken Term Detection Using Support Vector Machines and Weighted Pseudo Examples

Lee

2013

IEEE Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

Spoken term detection (STD) is a key technology for retrieval of spoken content, which will be very important to retrieve and browse multimedia content over the Internet. The discriminative capability of machine learning methods has recently been used to facilitate STD. This paper presents a new approach to improve STD using support vector machines (SVM) based on acoustic information. The concept of pseudo-relevance feedback (PRF) well used in the retrieval of text, image and video is used here. The basic idea of using PRF here is to assume some spoken segments in the first-pass retrieved results are relevant (or pseudorelevant) and some others irrelevant (or pseudo-irrelevant), and take these segments as positive and negative examples to train a query-specific SVM. This SVM is then used for re-ranking the firstpass retrieved results, and only the re-ranked results are shown to the user. In this paper, feature vectors representing the spoken segments based on acoustic information to be used in SVM are considered and analyzed. Furthermore, conventionally in PRF the items with the highest and lowest scores in the first-pass retrieved results are respectively taken as pseudo-relevant and -irrelevant, but in this way some incorrect examples are inevitably included in the training data especially when the recognition accuracy is poor. Here we further propose an enhanced SVM which not only better selects positive/negative examples considering the reliability of the spoken segments, but emphasizes more on more reliable training examples by modifying the SVM formulation. Experiments on two different sets of spoken archives with different speaking styles and different levels of recognition accuracies demonstrated significant improvements offered by the proposed approaches.

show abstract

Learning on demand - course lecture distillation by information extraction and semantic structuring for spoken documents

Cited by 15 publications

References 2 publications

Voice-based information retrieval — how far are we from the text-based information retrieval ?

Voice-based information retrieval — how far are we from the text-based information retrieval ?

Improved Semantic Retrieval of Spoken Content by Document/Query Expansion with Random Walk Over Acoustic Similarity Graphs

Enhanced Spoken Term Detection Using Support Vector Machines and Weighted Pseudo Examples

Contact Info

Product

Resources

About

Learning on demand - course lecture distillation by information extraction and semantic structuring for spoken documents

Cited by 15 publications

References 2 publications

Voice-based information retrieval &#x2014; how far are we from the text-based information retrieval ?

Voice-based information retrieval &#x2014; how far are we from the text-based information retrieval ?

Improved Semantic Retrieval of Spoken Content by Document/Query Expansion with Random Walk Over Acoustic Similarity Graphs

Enhanced Spoken Term Detection Using Support Vector Machines and Weighted Pseudo Examples

Contact Info

Product

Resources

About

Voice-based information retrieval — how far are we from the text-based information retrieval ?

Voice-based information retrieval — how far are we from the text-based information retrieval ?