Creating speaker independent ASR system through prosody modification based data augmentation

S Shahnawazuddin, N Adiga, HK Kathania… - Pattern Recognition …, 2020 - Elsevier
In this paper, the effect of prosody-modification-based data augmentation is explored in the
context of automatic speech recognition (ASR). The primary motive is to develop ASR …

[HTML][HTML] A formant modification method for improved ASR of children's speech

HK Kathania, SR Kadiri, P Alku, M Kurimo - Speech Communication, 2022 - Elsevier
Differences in acoustic characteristics between children's and adults' speech degrade
performance of automatic speech recognition systems when systems trained using adults' …

A text-to-speech pipeline, evaluation methodology, and initial fine-tuning results for child speech synthesis

R Jain, MY Yiwere, D Bigioi, P Corcoran… - IEEE Access, 2022 - ieeexplore.ieee.org
Speech synthesis has come a long way as current text-to-speech (TTS) models can now
generate natural human-sounding speech. However, most of the TTS research focuses on …

Addressing noise and pitch sensitivity of speech recognition system through variational mode decomposition based spectral smoothing

IC Yadav, S Shahnawazuddin, G Pradhan - Digital Signal Processing, 2019 - Elsevier
In this paper, we propose a novel front-end speech parameterization technique for automatic
speech recognition (ASR) that is less sensitive towards ambient noise and pitch variations …

In-domain and out-of-domain data augmentation to improve children's speaker verification system in limited data scenario

S Shahnawazuddin, W Ahmad… - ICASSP 2020-2020 …, 2020 - ieeexplore.ieee.org
In this paper, we present our efforts towards developing a robust automatic speaker
verification (ASV) system for children when the domain-specific data is limited. For that …

Creating robust children's ASR system in zero-resource condition through out-of-domain data augmentation

V Kumar, A Kumar, S Shahnawazuddin - Circuits, Systems, and Signal …, 2022 - Springer
Developing an automatic speech recognition (ASR) system for children's speech is
extremely challenging due to the unavailability of data from the child domain for the majority …

Spectral warping and data augmentation for low resource language ASR system under mismatched conditions

M Dua, V Kadyan, N Banthia, A Bansal, T Agarwal - Applied Acoustics, 2022 - Elsevier
The performance of an Automatic Speech Recognition System (ASR) system deteriorates
while using it on children speech, due to large variations and mismatch of acoustic and …

Children's speaker verification in low and zero resource conditions

S Shahnawazuddin, W Ahmad, N Adiga… - Digital Signal …, 2021 - Elsevier
Our efforts towards developing an automatic speaker verification (ASV) system for child
speakers are presented in this paper. For the majority of the languages, children's speech …

Developing children's ASR system under low-resource conditions using end-to-end architecture

S Shahnawazuddin - Digital Signal Processing, 2024 - Elsevier
The work presented in this paper aims at enhancing the performance of end-to-end (E2E)
speech recognition task for children's speech under low resource conditions. For majority of …

Developing speaker independent ASR system using limited data through prosody modification based on fuzzy classification of spectral bins

S Shahnawazuddin, N Adiga, BT Sai, W Ahmad… - Digital Signal …, 2019 - Elsevier
The primary motive of this study is to develop an automatic speech recognition (ASR) system
using limited amount of speech data such that it is least affected by speaker-dependent …