ASRoIL: a comprehensive survey for automatic speech recognition of Indian languages

Singh, Amitoj; Kadyan, Virender; Kumar, Munish; Bassan, Nancy

doi:10.1007/s10462-019-09775-8

Cited by 40 publications

(12 citation statements)

References 123 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to accessibility, speech signals contain many other emotional cues [4]. Although speech signals contain substantial amounts of information, it can be unrewarding to drop the linguistic component that coexists with it, especially given that the text component can be easily transcribed in real world applications with the considerable successes in the domain of speech-to-text with several commercial-scale APIs being available [5].…”

Section: Introductionmentioning

confidence: 99%

Jointly Fine-Tuning "BERT-like" Self Supervised Models to Improve Multimodal Speech Emotion Recognition

Siriwardhana¹,

Reis²,

Weerasekera³

et al. 2020

Preprint

View full text Add to dashboard Cite

Multimodal emotion recognition from speech is an important area in affective computing. Fusing multiple data modalities and learning representations with limited amounts of labeled data is a challenging task. In this paper, we explore the use of modality specific"BERT-like" pretrained Self Supervised Learning (SSL) architectures to represent both speech and text modalities for the task of multimodal speech emotion recognition. By conducting experiments on three publicly available datasets (IEMOCAP, CMU-MOSEI, and CMU-MOSI), we show that jointly fine-tuning "BERT-like" SSL architectures achieve state-of-the-art (SOTA) results. We also evaluate two methods of fusing speech and text modalities and show that a simple fusion mechanism can outperform more complex ones when using SSL models that have similar architectural properties to BERT.

show abstract

Section: Introductionmentioning

confidence: 99%

Jointly Fine-Tuning "BERT-like" Self Supervised Models to Improve Multimodal Speech Emotion Recognition

Siriwardhana¹,

Reis²,

Weerasekera³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…This paper tried to explore state-of-art speech recognition with respect to different feature and modeling approaches in Indian and non-Indian languages across the world. Singh et al [306] conducted a review of the spoken languages of India. The survey was conducted based on the relevant research articles published from 2000 to 2018.…”

Section: Inclusion/exclusion Criteriamentioning

confidence: 99%

Computational intelligence in processing of speech acoustics: a survey

Singh

Kaur

Kukreja

et al. 2022

Complex Intell. Syst.

Self Cite

View full text Add to dashboard Cite

Speech recognition of a language is a key area in the field of pattern recognition. This paper presents a comprehensive survey on the speech recognition techniques for non-Indian and Indian languages, and compiled some of the computational models used for processing speech acoustics. An immense number of frameworks are available for speech processing and recognition for languages persisting around the globe. However, a limited number of automatic speech recognition systems are available for commercial use. The gap between the languages being spoken around the globe and the technical support available to these languages are very few. This paper examined major challenges for speech recognition for different languages. Analysis of the literature shows that lack of standard databases availability of minority languages hinder the research recognition research across the globe. When compared with non-Indian languages, the research on speech recognition of Indian languages (except Hindi) has not achieved the expected milestone yet. Combination of MFCC and DNN–HMM classifier is most commonly used system for developing ASR minority languages, whereas in some of the majority languages, researchers are using much advance algorithms of DNN. It has also been observed that the research in this field is quite thin and still more research needs to be carried out, particularly in the case of minority languages.

show abstract

“…Several works on ASR system were carried out in the past decade using machine learning and deep learning models [1]. Deep speech and Listen Attend Spell is a end to end ASR models using neural network techniques [2][3].…”

Section: Figure 1: Audio Speech Recognitionmentioning

confidence: 99%

Analysis of Audio Visual Feature Extraction Techniques for AVSR System

Kumar¹,

Renuka²,

Priya³

2021

Proceedings of the First International Conference on Combinatorial and Optimization, ICCAP 2021, December 7-8 2021, Chennai, In

View full text Add to dashboard Cite

Recently, Speech technology has started to change the way the human communicate with devices. Speech as a medium of man-machine interaction has been gaining its importance in the modern computer/mobile era. As a result, many computer programs incorporate cutting-edge voice technologies to do diverse jobs. Feature extraction is the foremost step in speech recognition. Understanding the importance of feature extraction methods, this work demystifies the concept behind feature extraction techniques used in audio visual speech recognition.

show abstract

ASRoIL: a comprehensive survey for automatic speech recognition of Indian languages

Cited by 40 publications

References 123 publications

Jointly Fine-Tuning "BERT-like" Self Supervised Models to Improve Multimodal Speech Emotion Recognition

Jointly Fine-Tuning "BERT-like" Self Supervised Models to Improve Multimodal Speech Emotion Recognition

Computational intelligence in processing of speech acoustics: a survey

Analysis of Audio Visual Feature Extraction Techniques for AVSR System

Contact Info

Product

Resources

About