A new keyword spotting algorithm with pre-calculated optimal thresholds

Junkawitsch, Jochen; Neubauer, L.; Höge, Harald; Ruske, Günther

doi:10.1109/icslp.1996.607208

Cited by 26 publications

(18 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Spoken term detection is a relatively new task; it has, however, been intensively studied for more than a decade [1]. (We also regard keyword spotting as just another term for openvocabulary spoken term detection [2].)…”

Section: A Formulating the Spoken Term Detection Taskmentioning

confidence: 99%

Spoken term detection from noisy input

Gosztolya

Kovács

Tóth

2011

2011 6th IEEE International Symposium on Applied Computational Intelligence and Informatics (SACI)

View full text Add to dashboard Cite

Abstract-The aim of the spoken term detection task is to find the occurrence of user-entered keywords in an archive of audio recordings. The kind of techniques that are used usually are vocabulary-independent, using only the acoustic information available. In this scenario, however, we rely exclusively on the acoustic model, which is a drawback when it is unreliable; for example when the input is noisy. In this paper we investigate the possible accuracy of spoken term detection when the recordings were obtained using small-capacity, portable devices (wireless sensors) that have a quite low-quality microphone. The accuracy scores show, however, that despite the high amount of noise in the input recordings, our spoken term detection method can still produce an acceptable level of accuracy.

show abstract

Section: A Formulating the Spoken Term Detection Taskmentioning

confidence: 99%

Spoken term detection from noisy input

Gosztolya

Kovács

Tóth

2011

2011 6th IEEE International Symposium on Applied Computational Intelligence and Informatics (SACI)

View full text Add to dashboard Cite

show abstract

“…MFCC is a popular feature set, used in speech recognition, and based on the frequency domain of Mel scale for the human ear scale [3]. Mel-scale is based on filter bank processing.…”

Section: ) Mel-frequency Cepstral Coefficient (Mfcc)mentioning

confidence: 99%

“…Mel-scale is based on filter bank processing. The Mel-frequency scale formula is based on mathematical equation given by (3). (3) Steps to derive MFCC:…”

Section: ) Mel-frequency Cepstral Coefficient (Mfcc)mentioning

confidence: 99%

See 1 more Smart Citation

Audio Search Based on Keyword Spotting in Arabic Language

Awaid¹,

Fawzi²,

Kandil³

2014

IJACSA

View full text Add to dashboard Cite

Abstract-Keyword spotting is an important application of speech recognition. This research introduces a keyword spotting approach to perform audio searching of uttered words in Arabic speech. The matching process depends on the utterance nucleus which is insensitive to its context. For spotting the targeted utterances, the matched nuclei are expanded to cover the whole utterances. Applying this approach to Quran and standard Arabic has promising results. To improve this spotting approach, it is combined with a text search in case of the existence of a transcript. This can be applied on Quran as there is exact correspondence between the audio and text files of each verse. The developed approach starts by text search to identify the verses that include the target utterance(s). For each allocated verse, the occurrence(s) of the target utterance is determined.The targeted utterance (the reference) is manually segmented from an allocated verse. Then Keyword spotting is performed for the extracted reference to the corresponding audio file. The accuracy of the spotted utterances achieved 97%. The experiments showed that the use of the combined text and audio search has reduced the search time by 90% when compared with audio search only tested on the same content. The developed approach has been applied to non-transcribed audio files (preaches and News) for searching chosen utterances. The results are promising. The accuracy of spotting was around 84% in case of preaches and 88% in case of the news.

show abstract

“…In contrary to other architectures [2] [3] [4] [5] our previous keyword spotting system [1] used just a score threshold to indicate whether the keyword ends at a time or not. The scores have the meaning of a distance measure, that results in low scores in case of good matching.…”

Section: Introductionmentioning

confidence: 99%

Failure simulation for a phoneme HMM based keyword spotter

Holzapfel

Ruske²,

Höge³

1997 IEEE International Conference on Acoustics, Speech, and Signal Processing

Self Cite

View full text Add to dashboard Cite

A basic problem in keyword spotting is the fact that the keywords itself cannot be completely different from background speech. Therefore, false alarms arise from those parts of the keyword which are also contained in the background. The paper describes the favourable application of a model trellis which enables to test individual phoneme sequences with respect to their influence on the underlying phoneme HMMs in a statistical way. It is shown, that the Viterbi path highly is affected by those partly fitting phoneme groups.The probability of occurrance of these phoneme sequences is captured by a statistical "speech model" consisting of a Markov graph having an order up to 2. In this way sequences of 1, 2, or 3 phonemes are considered. By combining the model trellis and the statistical speech model, the probability of false alarms can be precalculated in advance, thus providing an useful measure for the suitability of the keyword under consideration. When the choice of keywords was optimized by this suitability measure in a practical application (spotting multicom 94.4 data) , the false alarm rate could be reduced by a factor of 3.5.

show abstract

A new keyword spotting algorithm with pre-calculated optimal thresholds

Cited by 26 publications

References 8 publications

Spoken term detection from noisy input

Spoken term detection from noisy input

Audio Search Based on Keyword Spotting in Arabic Language

Failure simulation for a phoneme HMM based keyword spotter

Contact Info

Product

Resources

About