Speech Recognition in Kannada using HTK and Julius: A Comparative Study

Sharma, Roshan S.; Paladugu, Sri Harsha; Priya, K. Jeeva; Gupta, Deepa

doi:10.1109/iccsp.2019.8698039

Cited by 11 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Speaking vocal commands directly to applications, instead of relying on a mouse and keyboard to manipulate text, accelerates communication in human-computer interactions. However, achieving accurate automatic speech recognition (ASR) remains a major challenge due to factors such as speaker and language variability, vocabulary size, and noise interference [10,11].…”

Section: Introductionmentioning

confidence: 99%

Afan Oromo Speech-Based Computer Command and Control: An Evaluation with Selected Commands

Teshite,

Mamo,

Calpotura

2023

Advances in Human-Computer Interaction

View full text Add to dashboard Cite

Speech-based computer command and control utilize natural speech to enable computers to understand human language and execute tasks through commands. However, there has been no study or development of a speech-based command and control system for Microsoft Word in Afan Oromo. The primary aim of this research is to investigate and develop a speech-based command and control system for Afan Oromo using a selected set of command-and-control words from MS Word. To accomplish this objective, a speech recognizer was developed using the HTK toolkit, employing a small vocabulary, isolated words, speaker independence, and HMM-based techniques. The translation of the selected MS command words from English to Afan Oromo was completed in order to develop this automatic speech-based computer command system. Audio recordings were obtained from 38 speakers (16 females and 22 males) aged between 18 and 40 years, based on their availability. Word-level speech recognition was performed using MFCC and data processing, which are widely used and are effective approaches in speech recognition. Out of a total of 64 MS command words, 54 words (84.37%) were used for training and 10 words (15.63%) were used for testing. Live and nonlive evaluation techniques were employed to assess the performance of the recognizer. The live recognizer, which considers variations in the environment, outperformed the nonlive recognizer due to the influence of neighboring phones. The performance results for the monophone tied state, triphone, and triphone-based recognizers were 78.12%, 86.87%, and 88.99%, respectively. Thus, the triphone-based recognizer exhibited the best performance among the nonlive recognizers. The challenges of limited resources in this research study were limited to investigate speech-based commands for computers using only selected MS commands, which play a crucial role in text processing. In order to evaluate a speech-based interface in a real environment, there were no components available for object-as-a-service. The experimental findings of this study demonstrated that if an adequate amount of language resources was available, a computer-based Afan Oromo speech-based interface for command-and-control purposes could be developed.

show abstract

Section: Introductionmentioning

confidence: 99%

Afan Oromo Speech-Based Computer Command and Control: An Evaluation with Selected Commands

Teshite,

Mamo,

Calpotura

2023

Advances in Human-Computer Interaction

View full text Add to dashboard Cite

show abstract

“…Some of the human speech (6) production terminologies are respiration that is inhaling and exhaling air to control vocal intensity and loudness, phonation is the determination of how voiced sounds are produced, articulation is the restriction of airflow in the vocal tract producing a word, oral/nasal resonance is the sound produced as it goes through the mouth/nose, prosody is the tone of speaker utterance that may be a question/command/irony/emphasis/inference, phoneme (7) smallest component that may cause a change in meaning, phone (8) is a basic unit of sound utterance, phonological responsiveness is capability of the audience to perceive words, phonemic responsiveness is the capability of the audience to recognize phonemes, phonemic transcripts use very few symbols of phonetics, a single phoneme for each, phonetic spelling is the confirmation of pronunciation of each single letter as a word, phonetic transcriptions are the illustrations of spoken speech sounds, phonetics (9) involves detailed analysis of human speech and its perception, acoustic phonetics (10) is the analysis of transmission of sounds from narrator to listener, phonology (11) is a subdivision of phonetics that analyzes phoneme pronunciation, articulatory phonetics (12) is a study of building spoken speech sounds by narrator, auditory phonetics (13) is the treatment and sensitivity of verbal communication, stress may be given to a syllable in a word for some words in a sentence, phonics is a subdivision of linguistics that is concerned with the spoken oral sound, phonotactics (14) is a branch for specifying the rules for a phoneme and articulators (15) are the movable speech organs in the speech production.…”

Section: Introductionmentioning

confidence: 99%

KHiTE: Multilingual Speech Acquisition to Monolingual Text Translation

Rudrappa¹,

Reddy²,

Hanumanthappa³

2023

IJST

View full text Add to dashboard Cite

Objectives: To develop a system that accepts cross-lingual spoken reviews consisting of two to four languages, translate to target language text for Indic languages namely Kannada, Hindi, Telugu and/or English termed as cross lingual speech identification and text translation system. Methods: Hybridization of software engineering models are used in natural languages for pre-processing such as noise removal and speech splitting to obtain phonemes. Combinatorial models namely Hidden-Markov-Model, Artificial Neural Networks, Deep Neural Networks and Convulutional Neural Networks were deployed for direct and indirect speech mapping. Trained corpus consisting of thousand phonemes in the form of wave files for each language considered is named as KHiTEShabdanjali. The basic parameters cosidered for training dataset are pause, pitch, sampling frequency, threshold etc. Findings: The research has resulted in the development of mono-lingual and multi-lingual speech identification, tool for processing of cross-lingual speech and language identification, mono-lingual, bi-lingual, tri-lingual and quad-lingual speech to monolingual text translation for the four languages. It is a generic approach and can be used for other regional languages of India by training the corpus with the selected language. Novelty: Cross-lingual speech identification and text translation system helps users in e-shopping by reducing the time incurred in making a decision to purchase a product having enough features at an economical price, e-tutoring, e-farming activities, digitizing, defence etc.

show abstract