A system for retrieving speech documents

Glavitsch, Ulrike; Schäuble, Peter

doi:10.1145/133160.133194

Cited by 46 publications

(34 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One makes use of special syllable-like indexing units derived from text (Glavitsch and Schauble 1992;Schäuble and Glavitsch 1994) while others use phone sequences (phone n-grams) generated by post-processing the output of a phonetic speech recognizer (Ng and Zobel 1998;Wechsler and Schauble 1995). There are also methods that search for the query terms on phonetic transcriptions or phone lattice representations of the speech messages instead of creating subword indexing terms (Dharanipragada et al 1998;James 1995;Jones et al 1996;Wechsler et al 1998).…”

Section: Motivationmentioning

confidence: 99%

Subword-based approaches for spoken document retrieval

Zue

2000

Speech Communication

148

109

View full text Add to dashboard Cite

This thesis explores approaches to the problem of spoken document retrieval (SDR), which is the task of automatically indexing and then retrieving relevant items from a large collection of recorded speech messages in response to a user specified natural language text query. We investigate the use of subword unit representations for SDR as an alternative to words generated by either keyword spotting or continuous speech recognition. Our investigation is motivated by the observation that word-based retrieval approaches face the problem of either having to know the keywords to search for a priori, or requiring a very large recognition vocabulary in order to cover the contents of growing and diverse message collections. The use of subword units in the recognizer constrains the size of the vocabulary needed to cover the language; and the use of subword units as indexing terms allows for the detection of new user-specified query terms during retrieval.Four research issues are addressed. First, what are suitable subword units and how well can they perform? Second, how can these units be reliably extracted from the speech signal? Third, what is the behavior of the subword units when there are speech recognition errors and how well do they perform? And fourth, how can the indexing and retrieval methods be modified to take into account the fact that the speech recognition output will be errorful?We first explore a range of subword units of varying complexity derived from error-free phonetic transcriptions and measure their ability to effectively index and retrieve speech messages. We find that many subword units capture enough information to perform effective retrieval and that it is possible to achieve performance comparable to that of text-based word units. Next, we develop a phonetic speech recognizer and process the spoken document collection to generate phonetic transcriptions. We then measure the ability of subword units derived from these transcriptions to perform spoken document retrieval and examine the effects of recognition errors on retrieval performance. Retrieval performance degrades for all subword units (to 60% of the clean reference), but remains reasonable for some subword units even without the use of any error compensation techniques. We then investigate a number of robust methods that take into account the characteristics of the recognition errors and try to compensate for them in an effort to improve spoken document retrieval performance when there are speech recognition errors. We study the methods individually and explore the effects of combining them. Using these robust methods improves retrieval performance by 23%. We also propose a novel approach to SDR where the speech recognition and information retrieval components are more tightly integrated. This is accomplished by developing new recognizer and retrieval models where the interface between the two 3 components is better matched and the goals of the two components are consistent with each other and with the overall goal of the combine...

show abstract

Section: Motivationmentioning

confidence: 99%

Subword-based approaches for spoken document retrieval

Zue

2000

Speech Communication

148

109

View full text Add to dashboard Cite

show abstract

“…For languages such as German or Marathi, compounds are written as single words and IR may benefit from linguistically motivated decompounding. Glavitsch and Schäuble [1992] and Schäuble and Glavitsch [1994] extract consonant-vowel-consonant (CVC) sequences as indexing features for retrieval of speech documents to obtain a more robust approach for noisy speech transcriptions. They select features based on document and collection frequency, and discrimination value.…”

Section: Sub-word Identification and Indexingmentioning

confidence: 99%

“…Consonant-vowel sequences (CV) and variant methods, including vowel-consonant sequences (VC), consonant-vowel-consonant sequences (CVC), and vowel-consonant-vowel sequences (VCV) were often used for noisy data, e.g. in speech retrieval [Glavitsch and Schäuble 1992].…”

Section: Sub-word Identificationmentioning

confidence: 99%

Sub-Word Indexing and Blind Relevance Feedback for English, Bengali, Hindi, and Marathi IR

Leveling

Jones

2010

ACM Transactions on Asian Language Information Processing

View full text Add to dashboard Cite

The Forum for Information Retrieval Evaluation (FIRE) provides document collections, topics, and relevance assessments for information retrieval (IR) experiments on Indian languages. Several research questions are explored in this paper: 1. how to create create a simple, languageindependent corpus-based stemmer, 2. how to identify sub-words and which types of sub-words are suitable as indexing units, and 3. how to apply blind relevance feedback on sub-words and how feedback term selection is affected by the type of the indexing unit. More than 140 IR experiments are conducted using the BM25 retrieval model on the topic titles and descriptions (TD) for the FIRE 2008 English, Bengali, Hindi, and Marathi document collections.The major findings are: The corpus-based stemming approach is effective as a knowledge-light term conflation step and useful in case of few language-specific resources. For English, the corpusbased stemmer performs nearly as well as the Porter stemmer and significantly better than the baseline of indexing words when combined with query expansion. In combination with blind relevance feedback, it also performs significantly better than the baseline for Bengali and Marathi IR.Sub-words such as consonant-vowel sequences and word prefixes can yield similar or better performance in comparison to word indexing. There is no best performing method for all languages. For English, indexing using the Porter stemmer performs best, for Bengali and Marathi, overlapping 3-grams obtain the best result, and for Hindi, 4-prefixes yield the highest MAP. However, in combination with blind relevance feedback using 10 documents and 20 terms, 6-prefixes for English and 4-prefixes for Bengali, Hindi, and Marathi IR yield the highest MAP.Sub-word identification is a general case of decompounding. It results in one or more index terms for a single word form and increases the number of index terms but decreases their average length. The corresponding retrieval experiments show that relevance feedback on sub-words benefits from selecting a larger number of index terms in comparison with retrieval on word forms. Similarly, selecting the number of relevance feedback terms depending on the ratio of word vocabulary size to sub-word vocabulary size almost always slightly increases information retrieval effectiveness compared to using a fixed number of terms for different languages.

show abstract

“…Intelligent and efficient information retrieval techniques allowing easy access to huge amount and various types of information become highly desired. With the advances in speech recognition technology, proper integration of information retrieval and speech recognition has been considered by many researchers [1][2][3][4][5][6]. Because Chinese language is not alphabetic and input of Chinese characters into computers is very difficult, a multi-modal interface for retrieving Chinese text/spoken documents is especially highly desired, and thus this framework is the primary focus of this paper.…”

Section: Introductionmentioning

confidence: 99%

Syllable-Based Chinese Text/Spoken Document Retrieval Using Text/Speech Queries

Bai

Chen

Wang

2000

Int. J. Patt. Recogn. Artif. Intell.

View full text Add to dashboard Cite

In order to solve the problem with the fast growth of Chinese information resources on the Internet, this paper deals with the problem of Chinese text and spoken document retrieval using both text and speech queries. By properly utilizing the monosyllabic structure of Chinese language, the proposed approach performs the statistical similarity estimation between the text/speech queries and the text/spoken documents directly at the phonetic level using syllable-based statistical information. Extensive experiments were performed and the preliminary results are very encouraging.

show abstract

A system for retrieving speech documents

Cited by 46 publications

References 22 publications

Subword-based approaches for spoken document retrieval

Subword-based approaches for spoken document retrieval

Sub-Word Indexing and Blind Relevance Feedback for English, Bengali, Hindi, and Marathi IR

Syllable-Based Chinese Text/Spoken Document Retrieval Using Text/Speech Queries

Contact Info

Product

Resources

About