EM-based phoneme confusion matrix generation for low-resource spoken term detection

Xu, Di; Wang, Yun; Metze, Florian

doi:10.1109/slt.2014.7078612

Cited by 8 publications

(6 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The goal of system combination [8,9,10] is to merge KWS results obtained on lattices generated by different underlying ASR systems. Another group is represented by score normalization methods, such as sum-to-one [9], query length normalization [10], keyword-specific thresholding [11] [12,13,14,15]. Finally, another group of postprocessing methods calibrates scores via optimizing the KWS metric [16,17,18,8].…”

Section: Related Workmentioning

confidence: 99%

Rescoring Keyword Search Confidence Estimates with Graph-Based Re-Ranking Using Acoustic Word Embeddings

Piunova¹,

Beck

Schlüter

et al. 2019

Interspeech 2019

View full text Add to dashboard Cite

Postprocessing of confidence scores in keyword search (KWS) task is known to be an efficient way of improving retrieval performance. In this paper, we extend the existing graph-based re-ranking algorithm proposed for KWS score calibration. We replace the originally used Dynamic Time Warping (DTW) distance measure between prospective hits with distances between their Acoustic Word Embeddings (AWEs) learned from Neural Networks. We argue that AWEs trained to discriminate between the same and different words should improve the graphbased re-ranking performance. Experimental results on two languages from IARPA Babel program show that our approach outperforms the DTW and improves the baseline KWS result between 3.0-7.5% relative on the Maximum Term Weighted Value (MTWV) measure. It was previously shown, that enhancing detection lists with keyword exemplars given high confidence, improved the algorithm performance. We additionally expanded the detection lists with negative query exemplars and observed further improvements in MTWV.

show abstract

Section: Related Workmentioning

confidence: 99%

Rescoring Keyword Search Confidence Estimates with Graph-Based Re-Ranking Using Acoustic Word Embeddings

Piunova¹,

Beck

Schlüter

et al. 2019

Interspeech 2019

View full text Add to dashboard Cite

show abstract

“…On the other hand, the subword-based approach has the unique advantage that it can detect terms that consist of words that are not in the vocabulary of the recognizer, i.e., out-ofvocabulary (OOV) terms. The combination of these two approaches has been proposed in order to exploit the relative advantages of word and subword-based strategies [17,32,33,36,44,[63][64][65][66][67][68][69][70].…”

Section: Spoken Term Detection Overviewmentioning

confidence: 99%

ALBAYZIN 2018 spoken term detection evaluation: a multi-domain international evaluation in Spanish

Tejedor

Toledano

López-Otero

et al. 2019

J AUDIO SPEECH MUSIC PROC.

View full text Add to dashboard Cite

Search on speech (SoS) is a challenging area due to the huge amount of information stored in audio and video repositories. Spoken term detection (STD) is an SoS-related task aiming to retrieve data from a speech repository given a textual representation of a search term (which can include one or more words). This paper presents a multi-domain internationally open evaluation for STD in Spanish. The evaluation has been designed carefully so that several analyses of the main results can be carried out. The evaluation task aims at retrieving the speech files that contain the terms, providing their start and end times, and a score that reflects the confidence given to the detection. Three different Spanish speech databases that encompass different domains have been employed in the evaluation: the MAVIR database, which comprises a set of talks from workshops; the RTVE database, which includes broadcast news programs; and the COREMAH database, which contains 2-people spontaneous speech conversations about different topics. We present the evaluation itself, the three databases, the evaluation metric, the systems submitted to the evaluation, the results, and detailed post-evaluation analyses based on some term properties (within-vocabulary/out-of-vocabulary terms, single-word/multi-word terms, and native/foreign terms). Fusion results of the primary systems submitted to the evaluation are also presented. Three different research groups took part in the evaluation, and 11 different systems were submitted. The obtained results suggest that the STD task is still in progress and performance is highly sensitive to changes in the data domain.

show abstract

“…A standard tool used in spoken term detection and speech recognition for quantifying variation is the phone confusion matrix [14] [16][17][18][19] which captures the confusion statistics between phones thus providing a way of defining commonalities or groups [20][21][22]. However, a confusion matrix can suffer from data sparseness due to the fact that although some phones may be phonetically similar, only a small number of confusions may be found with one or more other phones.…”

Section: Introductionmentioning

confidence: 99%

Enhancing Data-Driven Phone Confusions Using Restricted Recognition

Kane

Carson-Berndsen

2016

Interspeech 2016

View full text Add to dashboard Cite

This paper presents a novel approach to address data sparseness in standard confusion matrices and demonstrates how enhanced matrices, which capture additional similarities, can impact the performance of spoken term detection. Using the same training data as for the standard phone confusion matrix, an enhanced confusion matrix is created by iteratively restricting the recognition process to exclude one acoustic model per iteration. Since this results in a greater amount of confusion data for each phone, the enhanced confusion matrix encodes more similarities. The enhanced phone confusion matrices perform demonstrably better than standard confusion matrices on a spoken term detection task which uses both HMMs and DNNs.

show abstract

EM-based phoneme confusion matrix generation for low-resource spoken term detection

Cited by 8 publications

References 20 publications

Rescoring Keyword Search Confidence Estimates with Graph-Based Re-Ranking Using Acoustic Word Embeddings

Rescoring Keyword Search Confidence Estimates with Graph-Based Re-Ranking Using Acoustic Word Embeddings

ALBAYZIN 2018 spoken term detection evaluation: a multi-domain international evaluation in Spanish

Enhancing Data-Driven Phone Confusions Using Restricted Recognition

Contact Info

Product

Resources

About