Query expansion using local and global document analysis
SIGIR '96 Proceedings of the 19th annual international ACM SIGIR conference on Research and development in information retrieval
Self-organizing maps
Latent semantic indexing: a probabilistic analysis
PODS '98 Proceedings of the seventeenth ACM SIGACT-SIGMOD-SIGART symposium on Principles of database systems
Connectionist Speech Recognition: A Hybrid Approach
Connectionist Speech Recognition: A Hybrid Approach
The SMART Retrieval System—Experiments in Automatic Document Processing
The SMART Retrieval System—Experiments in Automatic Document Processing
The Cambridge University spoken document retrieval system
ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 01
ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 01
Speech recognition experiments using multi-span statistical language models
ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 02
Information fusion for spoken document retrieval
ICASSP '00 Proceedings of the Acoustics, Speech, and Signal Processing, 2000. on IEEE International Conference - Volume 04
The THISL Spoken Document Retrieval Project
ICMCS '99 Proceedings of the 1999 IEEE International Conference on Multimedia Computing and Systems - Volume 02
The use of artificial neural networks in the speech understanding model-SUM
ICANN'07 Proceedings of the 17th international conference on Artificial neural networks
Spoken Content Retrieval: A Survey of Techniques and Technologies
Foundations and Trends in Information Retrieval
| Hi-index | 0.00 |
A method is presented to provide a useful searchable index for spoken audio documents. The task differs from the traditional (text) document indexing, because large audio databases are decoded by automatic speech recognition and decoding errors occur frequently. The idea in this paper is to take advantage of the large size of the database and select the best index terms for each document with the help of the other documents close to it using a semantic vector space. First, the audio stream is converted into a text stream by a speech recognizer. Then the text of each story is represented in a vector space as a document vector which is the normalized sum of the word vectors in the story. A large collection of such document vectors is used to train a self-organizing map (SOM) to find latent semantic structures in the collection. As the stories in spoken news are short and will include speech recognition errors, smoothing of the document vectors using the semantic clusters determined by the SOM is introduced to enhance the indexing. The application in this paper is the indexing and retrieval of broadcast news on radio and television. Test results are given using the evaluation data from the text retrieval conference (TREC) spoken document retrieval (SDR) task.