Spoken Language Identification with Phonotactics Methods on Minangkabau, Sundanese, and Javanese Languages

Safitri, Nur Endah; Zahra, Amalia; Adriani, Mirna

doi:10.1016/j.procs.2016.04.047

Cited by 24 publications

(10 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Every language is composed of phonemes, which are distinct unit of sounds in that language, such as b of black and g of green. Several prosodic and acoustic features are based on phonemes, which become the underlying features on whom the performance of the statistical model depends [20,5]. If two languages have many overlapping phonemes, then identifying them becomes a challenging task for a classifier.…”

Section: Introductionmentioning

confidence: 99%

Spoken Language Identification Using ConvNets

Sarthak

Shukla

Mittal

2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Language Identification (LI) is an important first step in several speech processing systems. With a growing number of voice-based assistants, speech LI has emerged as a widely researched field. To approach the problem of identifying languages, we can either adopt an implicit approach where only the speech for a language is present or an explicit one where text is available with its corresponding transcript. This paper focuses on an implicit approach due to the absence of transcriptive data. This paper benchmarks existing models and proposes a new attention based model for language identification which uses log-Mel spectrogram images as input. We also present the effectiveness of raw waveforms as features to neural network models for LI tasks. For training and evaluation of models, we classified six languages (English, French, German, Spanish, Russian and Italian) with an accuracy of 95.4% and four languages (English, French, German, Spanish) with an accuracy of 96.3% obtained from the VoxForge dataset. This approach can further be scaled to incorporate more languages.

show abstract

Section: Introductionmentioning

confidence: 99%

Spoken Language Identification Using ConvNets

Sarthak

Shukla

Mittal

2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Safitri, et al [23] using the phone recognition method followed by language modeling (PRLM) and parallel phone recognition followed by language modeling (PPRLM) to identify the three selected languages. The difference between the two methods is the number of telephone identifiers used, if PRLM only uses one telephone identifier, PPRLM can use more than one telephone identifier for the language classification process.…”

Section: Introductionmentioning

confidence: 99%

Spoken language identification using i-vectors, x-vectors, PLDA and logistic regression

Abdurrahman

Zahra

2021

Bulletin EEI

Self Cite

View full text Add to dashboard Cite

In this paper, i-vector and x-vector is used to extract the features from speech signal from local Indonesia languages, namely Javanese, Sundanese and Minang languages to help classifier identify the language spoken by the speaker. Probabilistic linear discriminant analysis (PLDA) are used as the baseline classifier and logistic regression technique are used because of prior studies showing logistic regression has better performance than PLDA for classifying speech data. Once these features are extracted. The feature is going to be classified using the classifier mentioned before. In the experiment, we tried to segment the test data to three segment such as 3, 10, and 30 seconds. This study is expanded by testing multiple parameters on the i-vector and x-vector method then comparing PLDA and logistic regression performance as its classifier. The x-vector has better score than i-vector for every segmented data while using PLDA as its classifier, except where the i-vector and x-vector is using logistic regression, i-vector still has better accuracy compared to x-vector.

show abstract

“…Over the years, researchers have utilized many prosodic and acoustic features to construct machine learning models for LID systems [3]. Several prosodic and acoustic features are based on phonemes, which become the underlying features that drive the * These authors contributed equally to this work performance of the statistical models [4]. If two languages have many overlapping phonemes, then identifying them becomes a challenging task for a classifier.…”

Section: Introductionmentioning

confidence: 99%

Exploiting Spectral Augmentation for Code-Switched Spoken Language Identification

Rangan¹,

Teki²,

Misra³

2020

Preprint

View full text Add to dashboard Cite

Spoken language Identification (LID) systems are needed to identify the language(s) present in a given audio sample, and typically could be the first step in many speech processing related tasks such as automatic speech recognition (ASR). Automatic identification of the languages present in a speech signal is not only scientifically interesting, but also of practical importance in a multilingual country such as India. In many of the Indian cities, when people interact with each other, as many as three languages may get mixed. These may include the official language of that province, Hindi and English (at times the languages of the neighboring provinces may also get mixed during these interactions). This makes the spoken LID task extremely challenging in Indian context. While quite a few LID systems in the context of Indian languages have been implemented, most such systems have used small scale speech data collected internally within an organization. In the current work, we perform spoken LID on three Indian languages (Gujarati, Telugu, and Tamil) code-mixed with English. This task was organized by the Microsoft research team as a spoken LID challenge. In our work, we modify the usual spectral augmentation approach and propose a language mask that discriminates the language ID pairs, which leads to a noise robust spoken LID system. The proposed method gives a relative improvement of approximately 3-5% in the LID accuracy over a baseline system proposed by Microsoft on the three language pairs for two shared tasks suggested in the challenge.

show abstract

Spoken Language Identification with Phonotactics Methods on Minangkabau, Sundanese, and Javanese Languages

Cited by 24 publications

References 3 publications

Spoken Language Identification Using ConvNets

Spoken Language Identification Using ConvNets

Spoken language identification using i-vectors, x-vectors, PLDA and logistic regression

Exploiting Spectral Augmentation for Code-Switched Spoken Language Identification

Contact Info

Product

Resources

About