Signal Processing Cues to Improve Automatic Speech Recognition for Low Resource Indian Languages

Baby, Arun; S, Karthik Pandia D; Murthy, Hema A.

doi:10.21437/sltu.2018-6

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Along with our NITS‐LD, a subset of Indic database is also used as training set. The details of the Indic database are given in (Baby, Karthik Pandia, & Murthy, ).…”

Section: Methodsmentioning

confidence: 99%

Cascade convolutional neural network‐long short‐term memory recurrent neural networks for automatic tonal and nontonal preclassification‐based Indian language identification

Bhanja

Laskar

2020

Expert Systems

View full text Add to dashboard Cite

This work presents an automatic tonal/nontonal preclassification-based Indian language identification (LID) system. Languages are firstly classified into tonal and nontonal categories, and then, individual languages are identified from the languages of the respective categories. This work proposes the use of pitch Chroma and formant features for this task, and also investigates how Mel-frequency Cepstral Coefficients (MFCCs) complement these features. It further explores block processing (BP), pitch synchronous analysis (PSA)-and glottal closure regions (GCRs)-based approaches for feature extraction, using syllables as basic units. Cascade convolutional neural network (CNN)-long short-term memory (LSTM) model using syllable-level features has been developed. National Institute of Technology Silchar language database (NITS-LD) and OGI-Multilingual Telephone Speech Corpus (OGI-MLTS) have been used for experimental validation. The proposed system based on the score combination of Cascade CNN-LSTM models of Chroma (extracted from BP method), first two formants and MFCCs (both extracted from GCR method) reports the highest accuracies. In the preclassification stage, the observed accuracies are 91%, 87.3%, and 85.1% for NITS-LD, for 30 s, 10 s, and 3 s test data respectively. For OGI-MLTS database, the respective accuracies are 86.7%, 83.1%, and 80.6%. That amounts to absolute improvements of 11.6%, 12.3%, and 13.9% for NITS-LD, and 12.5%, 11.9%, and 12.6% for OGI-MLTS database with respect to that of the baseline system. The proposed preclassification-based LID system shows improvements of 7.3%, 6.4%, and 7.4% for NITS-LD and 6.1%, 6.7%, and 7.2% for OGI-MLTS database over the baseline system for the three respective test data conditions.

show abstract

“…Along with our NITS‐LD, a subset of Indic database is also used as training set. The details of the Indic database are given in (Baby, Karthik Pandia, & Murthy, ).…”

Section: Methodsmentioning

confidence: 99%

Cascade convolutional neural network‐long short‐term memory recurrent neural networks for automatic tonal and nontonal preclassification‐based Indian language identification

Bhanja

Laskar

2020

Expert Systems

View full text Add to dashboard Cite

show abstract

“…They built the corpora through web-scraping and employed native speakers to search the web for texts in their native languages. Babirye et al (2022) curated texts and speech datasets for 5 East African languages, including Kiswahili and 4 languages spoken in the country of Uganda. They employed both participatory approaches with local communities and web scraping of social media, Wikipedia and local news sites.…”

Section: Data Collection and African Low-resource Language Corporamentioning

confidence: 99%

Kencorpus: A Kenyan Language Corpus of Swahili, Dholuo and Luhya for Natural Language Processing Tasks

Wanjawa

Wanzare

Indede

et al. 2023

JLCL

View full text Add to dashboard Cite

Indigenous African languages are categorized as under-served in Natural Language Processing. They therefore experience poor digital inclusivity and information access. The processing challenge with such languages has been how to use machine learning and deep learning models without the requisite data. The Kencorpus project intends to bridge this gap by collecting and storing text and speech data that is good enough for data-driven solutions in applications such as machine translation, question answering and transcription in multilingual communities. The Kencorpus dataset is a text and speech corpus for three languages predominantly spoken in Kenya: Swahili, Dholuo and Luhya (three dialects of Lumarachi, Lulogooli and Lubukusu). Data collection was done by researchers who were deployed to the various data collection sources such as communities, schools, media, and publishers. The Kencorpus' dataset has a collection of 5,594 items, being 4,442 texts of 5.6 million words and 1,152 speech files worth 177 hours. Based on this data, other datasets were also developed such as Part of Speech tagging sets for Dholuo and the Luhya dialects of 50,000 and 93,000 words tagged respectively. We developed 7,537 Question-Answer pairs from 1,445 Swahili texts and also created a text translation set of 13,400 sentences from Dholuo and Luhya into Swahili. The datasets are useful for downstream machine learning tasks such as model training and translation. Additionally, we developed two proof of concept systems: for Kiswahili speech-to-text and a machine learning system for Question Answering task. These proofs provided results of a performance of 18.87% word error rate for the former, and 80% Exact Match (EM) for the latter system. These initial results give great promise to the usability of Kencorpus to the machine learning community. Kencorpus is one of few public domain corpora for these three low resource languages and forms a basis of learning and sharing experiences for similar works especially for low resource languages. Challenges in developing the corpus included deficiencies in the data sources, data cleaning challenges, relatively short project timelines and the Coronavirus disease (COVID-19) pandemic that restricted movement and hence the ability to get the data in a timely manner.

show abstract

Signal Processing Cues to Improve Automatic Speech Recognition for Low Resource Indian Languages

Cited by 2 publications

References 0 publications

Cascade convolutional neural network‐long short‐term memory recurrent neural networks for automatic tonal and nontonal preclassification‐based Indian language identification

Cascade convolutional neural network‐long short‐term memory recurrent neural networks for automatic tonal and nontonal preclassification‐based Indian language identification

Kencorpus: A Kenyan Language Corpus of Swahili, Dholuo and Luhya for Natural Language Processing Tasks

Contact Info

Product

Resources

About