Spoken Language Identification of Indian Languages Using MFCC Features

Biswas, Mainak; Rahaman, Saif; Kundu, Satwik; Singh, Pawan Kumar; Sarkar, Ram

doi:10.1007/978-981-15-9492-2_12

Cited by 7 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then we gradually decrease the nodes to 64 and 32 to make it suitable for the output layer. The model is optimised by RMSprop (Root Mean Squared Propagation) using sparse categorical cross-entropy as a loss function, given by Equations ( 6) and (7). One of the reasons for using RMSprop as an optimizer is that it converges much faster to the local minima.…”

Section: Experiments and Resultsmentioning

confidence: 99%

“…Value of J ranges from 0 to 5 to determine number of categories in which an audio sample is to be classified. CCE = − ∑ 𝑡 𝑗 log(S(𝑥) 𝑗 ) 5 𝑗=0 (7) In the above equation S(x)j defines Softmax probability for the j-th class and tj represents the truth label.…”

Section: S(𝑥) 𝑖 =mentioning

confidence: 99%

“…The feature extraction procedure is the most effective and critical phase in any pattern recognition activity and depends on the selection and calculation of features. The most often utilised LID characteristics are MFCC features [6][7][8][9] which have achieved great accuracy. It also depends on various types of parameters, like demand, computer resources available, and the amount of language data available, all of which impact the reason for picking appropriate language recognition capabilities.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A comparison of cepstral and spectral features using recurrent neural network for spoken language identification

Thukroo,

Bashir,

Giri

2024

Comput. Artif. Intell.

View full text Add to dashboard Cite

Spoken language identification is the process of confirming labels regarding the language of an audio slice regardless of various features such as length, ambiance, duration, topic or message, age, gender, region, emotions, etc. Language identification systems are of great significance in the domain of natural language processing, more specifically multi-lingual machine translation, language recognition, and automatic routing of voice calls to particular nodes speaking or knowing a particular language. In his paper, we are comparing results based on various cepstral and spectral feature techniques such as Mel-frequency Cepstral Coefficients (MFCC), Relative spectral-perceptual linear prediction coefficients (RASTA-PLP), and spectral features (roll-off, flatness, centroid, bandwidth, and contrast) in the process of spoken language identification using Recurrent Neural Network-Long Short Term Memory (RNN-LSTM) as a procedure of sequence learning. The system or model has been implemented in six different languages, which contain Ladakhi and the five official languages of Jammu and Kashmir (Union Territory). The dataset used in experimentation consists of TV audio recordings for Kashmiri, Urdu, Dogri, and Ladakhi languages. It also consists of standard corpora IIIT-H and VoxForge containing English and Hindi audio data. Pre-processing of the dataset is done by slicing different types of noise with the use of the Spectral Noise Gate (SNG) and then slicing into audio bursts of 5 seconds duration. The performance is evaluated using standard metrics like F1 score, recall, precision, and accuracy. The experimental results showed that using spectral features, MFCC and RASTA-PLP achieved an average accuracy of 76%, 83%, and 78%, respectively. Therefore, MFCC proved to be the most convenient feature to be exploited in language identification using a recurrent neural network long short-term memory classifier.

show abstract

Section: Experiments and Resultsmentioning

confidence: 99%

Section: S(𝑥) 𝑖 =mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A comparison of cepstral and spectral features using recurrent neural network for spoken language identification

Thukroo,

Bashir,

Giri

2024

Comput. Artif. Intell.

View full text Add to dashboard Cite

show abstract

“…MFCCs [2], SDC [3], i-Vector [4], Linear Discriminant Analysis [LDA] [5], and x-vector [6] are the primary conventional methods used for spoken language identification. A mel-spectrogram combined with a Convolutional Recurrent Neural Network [CRNN], X-vector combined with DNN and Wave2Vec speech representations was tested in [7] and it showed the highest F1-score of 91%.…”

Section: Literature Reviewmentioning

confidence: 99%

The Effect of Synthetic Voice Data Augmentation on Spoken Language Identification on Indian Languages

Ambili,

Roy

2023

IEEE Access

View full text Add to dashboard Cite

Multilingual based voice activated human computer interaction systems are currently in high demand. The Spoken Language Identification Unit (SPLID) is an inevitable front end unit of such a multilingual system. These systems will be a great boon to a country like India where around 24 official languages are spoken. Deep learning architectures for spoken language identification have progressed to the point that they can now perform well, even in the presence of various background noises. However, a strong phonetic relationship across various Indian languages leads to increased confusion in the SPLID unit. Therefore, the goal of this study is to propose a synthetic voice data augmentation method based on speech synthesis to improve the spoken Indian language identification system. Here the research attempts to determine how well pre-trained computer vision models recognize spoken languages in synthetic and classical audio augmentation environments. The accuracy of the models was compared using bottleneck features extracted from three different pre-trained models VGG16, RESNET50, and Inception-v3 while using an Artificial Neural Network (ANN), Support Vector Machine (SVM), Logistic Regression (LR), Random Forest (RF), Naive Bayes (NB), Decision Tree (DT) and KNN (K-Nearest Neighbors) as classifiers.The proposed system was tested on three Indian language datasets -two comprising seven Indian languages (Hindi, Malayalam, Tamil, Telugu, Marathi, Kannada and Bengali), one containing five Indian languages (Tamil, Hindi, Malayalam, Oria and Assamese), and on a foreign language dataset. It was found that the addition of synthetic audio samples improved the accuracy by 17%. Among the pre-trained models, VGG16 and Inception-v3 combined with PCA and ANN were found to have the maximum accuracy of 97% .

show abstract

Speech Emotion Recognition Using Deep CNNs Trained on Log-Frequency Spectrograms

Biswas,

Sahu,

Agrebi

et al. 2023

Studies in Big Data

View full text Add to dashboard Cite

Spoken Language Identification of Indian Languages Using MFCC Features

Cited by 7 publications

References 12 publications

A comparison of cepstral and spectral features using recurrent neural network for spoken language identification

A comparison of cepstral and spectral features using recurrent neural network for spoken language identification

The Effect of Synthetic Voice Data Augmentation on Spoken Language Identification on Indian Languages

Speech Emotion Recognition Using Deep CNNs Trained on Log-Frequency Spectrograms

Contact Info

Product

Resources

About