A feature-based hierarchical speech recognition system for Hindi

Samudravijaya, K.; Ahuja, Ravin; Bondale, Nandini; Jose, T. J. Benedict; Krishnan, S.; Poddar, P.; Rao, xxPVS; Raveendran, Ramya

doi:10.1007/bf02745745

Cited by 9 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the journal Sadhana in 1998, a work [32] has been reported by Samudravijaya et al, where they have presented a description of a speech recognition system for Hindi. The system follows a hierarchic approach to speech recognition and integrates multiple knowledge sources within statistical pattern recognition paradigms at various stages of signal decoding.…”

Section: Statistical Approachmentioning

confidence: 92%

Speech Recognition in Indian Languages—A Survey

Sarma

2015

Recent Trends in Intelligent and Emerging Systems

View full text Add to dashboard Cite

In this paper, a brief overview derived out of detailed survey of speech recognition works reported in Indian languages is described. Robustness of speech recognition systems toward language variation is the recent trend of research in speech recognition technology. To develop a system which can communicate with human in any language like any other human is the foremost requirement in order to design appropriate speech recognition technology for one to all. India is a country which has vast linguistic variations among its billion plus population. Therefore, it provides a sound area of research toward language-specific speech recognition technology. From the beginning of the commercial availability of the speech recognition system, the technology has been dominated by the hidden Markov model (HMM) methodology due to its capability of modeling temporal structures of speech and encoding them as a sequence of spectral vectors. Most of the work done in Indian languages also uses HMM technology. However, from the last 10-15 years after the acceptance of neurocomputing as an alternative to HMM, artificial neural network (ANN)-based methodologies have started to receive attention for application in speech recognition. This is a trend worldwide as part of which few works have also been reported by a few researchers.

show abstract

Section: Statistical Approachmentioning

confidence: 92%

Speech Recognition in Indian Languages—A Survey

Sarma

2015

Recent Trends in Intelligent and Emerging Systems

View full text Add to dashboard Cite

show abstract

“…The necessity of the ASR system for native languages is becoming the need of the day because of the necessity to access online applications for day-to-day work, more so in the post-pandemic world. The philosophy of the Hindi ASR system is explained (Samudravijaya et al, 1998) by developing a hierarchical model in which speech-specific knowledge is integrated with pattern recognition techniques (semi-Markov model). A Hidden Markov Model Toolkit (HTK) based acoustic model for recognizing isolated words (having 30 words) has achieved an overall 94.63% accuracy (Kumar & Aggarwal, 2011).…”

Section: Review On Asr For Indian Languagesmentioning

confidence: 99%

“…Our work here addresses Hindi phoneme recognition using hierarchical approach that is an important step considering the heavy usage of Hindi-Devanagari phonemes in India, which is one of the most populous countries. As mentioned in Section 2.2, one hierarchical ASR model was developed for Hindi earlier (Samudravijaya et al, 1998), but that study did not consider different ML tools and separate feature sets at different levels of hierarchy, as we have done here. We believe that our model would provide an efficient and generic framework for all Indian languages which are either originated from Devanagari script (e.g., Hindi, Marathi, Konkani and Sanskrit) or follow the Devanagari phonetic structure (e.g., Bengali, Assamese and Odia).…”

Section: Takeawaysmentioning

confidence: 99%

A hierarchical automatic phoneme recognition model forHindi‐Devanagariconsonants using machine learning technique

Malakar

Keskar

Zadgaonkar³

2023

Expert Systems

View full text Add to dashboard Cite

A phoneme is perceptually the smallest distinct sound unit distinguished among words in a particular language. Every language has its own set of phonemes, and all the words are ordered sequences of phonemes. Therefore, phoneme recognition is essential to automatic speech recognition (ASR) systems. Phonemes of a language can be classified together using a single machine learning (ML) model through the direct classification (also known as the baseline or flat classification) approach. However, it is observed that the performance of such phoneme recognition degrades with the increase in the number of phoneme classes. The challenge is pronounced in languages with a larger number of phoneme classes, like Hindi, which has 48 phonemes.In this paper, we propose a speaker-independent hierarchical classification approach for 33 Hindi-Devanagari consonants/phonemes using cepstral features with ML techniques like support vector machine (SVM), random forest (RF) and fully connected deep neural network (DNN). In this hierarchical approach, a given phoneme is classified into successive subgroups until the particular phoneme class is identified.To perform the classification task, a binary or multi-class classifier is invoked for each internal (non-leaf) node in the hierarchy tree. Our model identified pairs of Optimal Feature Sets (based on mutual information) and the best suitable ML classifier for each internal decision node in the hierarchy using 10-fold cross-validation to help in efficient classification. Our proposed hierarchical model leads to better accuracy and 57% improved performance for phoneme recognition compared with the non-hierarchical, that is, the direct classification approach.

show abstract

“…isolated word speech recognition systems in Indian languages have already been developed and reported (Samudravijaya et al 1998;Rao et al 1996). The speech recognition module used with the web reader uses hidden Markov model (Rabiner 1989) to recognize the user's spoken commands.…”

mentioning

confidence: 99%

Indian accent text-to-speech system for web browsing

Sen

Samudravijaya

2002

Sadhana

View full text Add to dashboard Cite

Incorporation of speech and Indian scripts can greatly enhance the accessibility of web information among common people. This paper describes a 'web reader' which 'reads out' the textual contents of a selected web page in Hindi or in English with Indian accent. The content of the page is downloaded and parsed into suitable textual form. It is then passed on to an indigenously developed text-to-speech system for Hindi/Indian English, to generate spoken output. The text-to-speech conversion is performed in three stages: text analysis, to establish pronunciation, phoneme to acoustic-phonetic parameter conversion and, lastly, parameter-to-speech conversion through a production model. Different types of voices are used to read special messages. The web reader detects the hypertext links in the web pages and gives the user the option to follow the link or continue perusing the current web page. The user can exercise the option either through a keyboard or via spoken commands. Future plans include refining the web parser, improvement of naturalness of synthetic speech and improving the robustness of the speech recognition system.

show abstract

A feature-based hierarchical speech recognition system for Hindi

Cited by 9 publications

References 14 publications

Speech Recognition in Indian Languages—A Survey

Speech Recognition in Indian Languages—A Survey

A hierarchical automatic phoneme recognition model forHindi‐Devanagariconsonants using machine learning technique

Indian accent text-to-speech system for web browsing

Contact Info

Product

Resources

About