Effect of language independent transcribers on spoken language identification for different Indian languages

Saikia, Rajlakshmi; Singh, Shubra; Sarmah, Priyankoo

doi:10.1109/ialp.2017.8300582

Cited by 6 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Earlier, Automatic SLID systems were built using language dependent speech to-text synthesizers. Saikia R. et al [17] presents the response of Language Independent speech to text transcribers for various Indian languages. This closely relates to the need for deep learning in order to overcome the lack of accuracy in traditional LID systems.…”

Section: Literature Surveymentioning

confidence: 99%

“…Features Languages Accuracy Verma et al [12] SVM 3 81% Gupta et al [13] MFCC with random forest and SVM 4 92.6% Madhu et al [14] Phonotactic and Prosodic 7 72% and 68% Rao et al [15] MFCC,GMM 27 58.14% S. Palanivel et al [16] MFCC,GMM,HMM and ANN 9 80.56% Saikia et al [17] Transcription-based 7 96% Himadri M et al [2] CNN 7 95.52% Proposed CNN 7 98.86%…”

Section: Algorithmmentioning

confidence: 99%

See 1 more Smart Citation

Indian Language Identification using Deep Learning

2020

View full text Add to dashboard Cite

Spoken language is the most regular method of correspondence in this day and age. Endeavours to create language recognizable proof frameworks for Indian dialects have been very restricted because of the issue of speaker accessibility and language readability. However, the necessity of SLID is expanding for common and safeguard applications day by day. Feature extraction is a basic and important procedure performed in LID. A sound example is changed over into a spectrogram visual portrayal which describes a range of frequencies in regard with time. Three such spectrogram visuals were generated namely Log Spectrogram, Gammatonegram and IIR-CQT Spectrogram for audio samples from the standardized IIIT-H Indic Speech Database. These visual representations depict language specific details and the nature of each language. These spectrograms images were then used as an input to the CNN. Classification accuracy of 98.86% was obtained using the proposed methodology.

show abstract

Section: Literature Surveymentioning

confidence: 99%