Neural network based recognition of speech using MFCC features

Barua, Pialy; Ahmad, Kanij; Khan, Ainul Anam Shahjamal; Sanaullah, Muhammad

doi:10.1109/iciev.2014.6850680

Cited by 14 publications

(1 citation statement)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MFCC and GFCC features are widely used in different speech processing applications e.g. automatic speech recognition (ASR) [45], deceptive speech detection [46], speaker identification, language identification and native language identification etc. The major difference between spectrogram and cochleagram is that spectrogram features are based on Mel scale and cochleagram features are based on equivalent rectangular bandwidth (ERB) scale which has better resolution at low frequencies.…”

Section: Featuresmentioning

confidence: 99%

Native Language Identification in Very Short Utterances Using Bidirectional Long Short-Term Memory Network

Adeeba

Hussain

2019

IEEE Access

View full text Add to dashboard Cite

Native language identification (NLI) is the task of identifying the first language of a user based on their speech or written text in a second language. In this paper, we propose the use of spectrogramand cochleagram-based features extracted from very short speech utterances (0.8 s on average) to infer the native language of an Urdu speaker. The bidirectional long short-term memory (BLSTM) neural networks are adopted for the classification of utterances among the native languages. A set of experiments is carried out for the network architecture search and the system's accuracy is evaluated on the validation data set. Overall accuracy of 74.81% and 71.61% is achieved using the Mel-frequency cepstral coefficients (MFCC) and Gammatone frequency cepstral coefficients (GFCC), respectively. Moreover, the optimized MFCC featurebased BLSTM network and GFCC feature-based BLSTM network are merged together to take advantage of both the feature sets. The experiments show that the performance of the merged network surpasses the individual BLSTM networks and accuracy of 75.69% is achieved on the evaluation data. The effect of test data duration is also analyzed (from 0.27 s to 1.5 s); in addition, it is observed that with very short duration as 0.4 s, an accuracy of over 50% can be achieved.

show abstract

Section: Featuresmentioning

confidence: 99%