Confidence index dynamic time warping for language-independent embedded speech recognition

Zhang, Xianglilan; Sun, Jiping; Luo, Zhigang; Li, Ming

doi:10.1109/icassp.2013.6639236

Cited by 6 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Under quiet environment and bad recording condition (Speaker ), OAWDTW improves the accuracy by about 0.5% and acquires a 9.09% RRER. As DTW already does almost perfect speech recognition under quiet environment [27] [33] – [34] , it is likely that we will not get any improvement by using OAWDTW. Thus it is encouraging that our OAWDTW achieves a little better recognition accuracy for bad recording condition.…”

Section: Resultsmentioning

confidence: 99%

“…It is noted that these weighted DTW do not decrease time complexities. We have developed confidence index dynamic time warping (CIDTW) [27] and merge-weighted dynamic time warping (MWDTW) [28] methods of fast and accurate speech recognition for clean speech data. Both methods involve a merging step that merges adjacent similar time frames in one speech signal and then performs DTW on merged speech data.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

One-against-All Weighted Dynamic Time Warping for Language-Independent and Speaker-Dependent Speech Recognition in Adverse Conditions

Zhang

Sun²,

Luo

2014

PLoS ONE

Self Cite

View full text Add to dashboard Cite

Considering personal privacy and difficulty of obtaining training material for many seldom used English words and (often non-English) names, language-independent (LI) with lightweight speaker-dependent (SD) automatic speech recognition (ASR) is a promising option to solve the problem. The dynamic time warping (DTW) algorithm is the state-of-the-art algorithm for small foot-print SD ASR applications with limited storage space and small vocabulary, such as voice dialing on mobile devices, menu-driven recognition, and voice control on vehicles and robotics. Even though we have successfully developed two fast and accurate DTW variations for clean speech data, speech recognition for adverse conditions is still a big challenge. In order to improve recognition accuracy in noisy environment and bad recording conditions such as too high or low volume, we introduce a novel one-against-all weighted DTW (OAWDTW). This method defines a one-against-all index (OAI) for each time frame of training data and applies the OAIs to the core DTW process. Given two speech signals, OAWDTW tunes their final alignment score by using OAI in the DTW process. Our method achieves better accuracies than DTW and merge-weighted DTW (MWDTW), as 6.97% relative reduction of error rate (RRER) compared with DTW and 15.91% RRER compared with MWDTW are observed in our extensive experiments on one representative SD dataset of four speakers' recordings. To the best of our knowledge, OAWDTW approach is the first weighted DTW specially designed for speech data in adverse conditions.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

One-against-All Weighted Dynamic Time Warping for Language-Independent and Speaker-Dependent Speech Recognition in Adverse Conditions

Zhang

Sun²,

Luo

2014

PLoS ONE

Self Cite

View full text Add to dashboard Cite

show abstract

“…The problems with the original DTW formulation are its high computational burden, the low performance in speaker independent tasks and the discrimination between in-domain and out-ofdomain sentences. In the literature, particular attention has been devoted to develop efficient versions of DTW for devices with limited computational resources [5][6][7].…”

Section: Introductionmentioning

confidence: 99%

Acoustic template-matching for automatic emergency state detection: An ELM based algorithm

et al. 2015

View full text Add to dashboard Cite

“…That is, speeding up DTW process at the expense of accuracy. On the other hand, considering that DTW gives each time frame equal weight to align two time series, the authors of [13] and [14] introduced two weighted DTW methods to avoid potential misclassification caused by equal weight. It is noted that these weighted DTW do not decrease time complexities.…”

Section: Introductionmentioning

confidence: 99%

A Novel Weighted Dynamic Time Warping for Light Weight Speaker-Dependent Speech Recognition in Noisy and Bad Recording Conditions

Zhang

Sun

Huang

et al. 2014

AMM

View full text Add to dashboard Cite

Lightweight speaker-dependent (SD) automatic speech recognition (ASR) is a promising solution for the problems of possibility of disclosing personal privacy and difficulty of obtaining training material for many seldom used English words and (often non-English) names. Dynamic time warping (DTW) algorithm is the state-of-the-art algorithm for small foot-print SD ASR applications, which have limited storage space and small vocabulary. In our previous work, we have successfully developed two fast and accurate DTW variations for clean speech data. However, speech recognition in adverse conditions is still a big challenge. In order to improve recognition accuracy in noisy and bad recording conditions, such as too high or low recording volume, we introduce a novel weighted DTW method. This method defines a feature index for each time frame of training data, and then applies it to the core DTW process to tune the final alignment score. With extensive experiments on one representative SD dataset of three speakers' recordings, our method achieves better accuracy than DTW, where 0.5% relative reduction of error rate (RRER) on clean speech data and 7.5% RRER on noisy and bad recording speech data. To the best of our knowledge, our new weighted DTW is the first weighted DTW method specially designed for speech data in noisy and bad recording conditions.

show abstract

Confidence index dynamic time warping for language-independent embedded speech recognition

Cited by 6 publications

References 15 publications

One-against-All Weighted Dynamic Time Warping for Language-Independent and Speaker-Dependent Speech Recognition in Adverse Conditions

One-against-All Weighted Dynamic Time Warping for Language-Independent and Speaker-Dependent Speech Recognition in Adverse Conditions

Acoustic template-matching for automatic emergency state detection: An ELM based algorithm

A Novel Weighted Dynamic Time Warping for Light Weight Speaker-Dependent Speech Recognition in Noisy and Bad Recording Conditions

Contact Info

Product

Resources

About