Improvement of phone recognition accuracy using speech mode classification

Tripathi, Kumud; Rao, K. Sreenivasa

doi:10.1007/s10772-017-9483-4

Cited by 13 publications

(9 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed features corresponding to PAU-DL and KSVD based dictionaries are named as Fpau and F ksvd , respectively. The performance of proposed features is compared with conventional MFCC and combination of spectral, prosodic and excitation source features discussed in [3]. The prosodic details are collected from pitch and energy contour of a speech signal whereas, MFCCs are representing the spectral information of speech.…”

Section: Experiments and Resultsmentioning

confidence: 99%

“…In our earlier work [3], we had developed the speech mode classifier for Bengali speech corpus using spectral, excitation source and prosodic features. In our current work, we have explored five other languages for better comparison among the proposed sparse based features and previously explored features.…”

Section: Experiments and Resultsmentioning

confidence: 99%

“…From Table 1, it is clear that combination of MFCCs and proposed features are giving similar results as compared to the combination of spectral, excitation source and prosodic features. The major significance of our proposed features over the features described in [3] is (i) it reduced mathematical complexity by reducing the feature dimension and (ii) it gives better performance than spectral, excitation source and prosodic features.…”

Section: Experiments and Resultsmentioning

confidence: 99%

“…In our earlier work [3], the speech mode classifier is developed for Bengali speech corpus using vocal tract, prosodic, and excitation source features. The performance of SMC was 98% at very high computation cost.…”

Section: Introductionmentioning

confidence: 99%

“…The performance of SMC was 98% at very high computation cost. Therefore, in our current work, we have proposed a sparse based feature which has the better capability of discriminating between the modes at low computation cost in comparison to vocal tract, prosodic, and excitation source features discussed in [3].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Analysis of sparse representation based feature on speech mode classification

Tripathi

Rao

2018

Interspeech 2018

Self Cite

View full text Add to dashboard Cite

Traditional phone recognition systems are developed using read speech. But, in reality, the speech that needs to be processed by machine is not always in read mode. Therefore to handle the phone recognition in realistic scenarios, three broad modes of speech: read, conversation and extempore are considered in this study. The conversation mode includes informal communication in an unconstrained environment between two or more individuals. In the extempore mode, a person speaks with confidence without the help of notes. Read mode is a formal type of speech in a rigid environment. In this work, we have proposed a sparse based feature for speech mode classification. The effectiveness of sparse representation depends on the dictionary. Therefore, we have learned multiple overcomplete dictionaries by using parallel atom-update dictionary learning (PAU-DL) technique to capture the discrimination characteristics present in the considered speech modes. Further, sparse features correspond to the sequence of speech frames are derived using the learned dictionary by applying the orthogonal matching pursuit (OMP) algorithm. The proposed sparse features are evaluated on speech corpora consisting of six Indian languages by performing classification of speech modes. The results with the proposed sparse features outperform the standard spectral, excitation source and prosodic features.

show abstract

Section: Experiments and Resultsmentioning

confidence: 99%

Section: Experiments and Resultsmentioning

confidence: 99%

Section: Experiments and Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations