Nagaraj Adiga
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Nagaraj Adiga has a total of 75 co-authors. Here are the top co-authors by number of shared publications:
- Syed Shahnawazuddin
National Institute of Technology Patna
6 shared publications S. R. Mahadeva Prasanna
Department of Electronics and Electrical Engineering, Indian Institute of Technology Guwahati
5 shared publicationsS.R. Mahadeva Prasanna
4 shared publicationsHemant K. Kathania
3 shared publicationsB Tarun Sai
2 shared publicationsBidisha Sharma
EEE, Indian Institute of Technology Guwahati, Assam, India
2 shared publications
Latest Publications
- Open Access
- 26 August 2021
- Published by International Speech Communication Association
- p. 154-159
Non-native English lexicon creation for bilingual speech synthesis
- 26 August 2021
- Published by International Speech Communication Association
- p. 154-159
Open AccessNon-native English lexicon creation for bilingual speech synthesis
- Open Access
An ASR Guided Speech Intelligibility Measure for TTS Model Selection
The perceptual quality of neural text-to-speech (TTS) is highly dependent on the choice of the model during training. Selecting the model using a training-objective metric such as the least mean squared error does not always correlate with human perception. In this paper, we propose an objective metric based on the phone error rate (PER) to select the TTS model with the best speech intelligibility. The PER is computed between the input text to the TTS model, and the text decoded from the synthesized speech using an automatic speech recognition (ASR) model, which is trained on the same data as the TTS model. With the help of subjective studies, we show that the TTS model chosen with the least PER on validation split has significantly higher speech intelligibility compared to the model with the least training-objective metric loss. Finally, using the proposed PER and subjective evaluation, we show that the choice of best TTS model depends on the genre of the target domain text. All our experiments are conducted on a Hindi language dataset. However, the proposed model selection method is language independent.
Open AccessAn ASR Guided Speech Intelligibility Measure for TTS Model Selection
The perceptual quality of neural text-to-speech (TTS) is highly dependent on the choice of the model during training. Selecting the model using a training-objective metric such as the least mean squared error does not always correlate with human perception. In this paper, we propose an objective metric based on the phone error rate (PER) to select the TTS model with the best speech intelligibility. The PER is computed between the input text to the TTS model, and the text decoded from the synthesized speech using an automatic speech recognition (ASR) model, which is trained on the same data as the TTS model. With the help of subjective studies, we show that the TTS model chosen with the least PER on validation split has significantly higher speech intelligibility compared to the model with the least training-objective metric loss. Finally, using the proposed PER and subjective evaluation, we show that the choice of best TTS model depends on the genre of the target domain text. All our experiments are conducted on a Hindi language dataset. However, the proposed model selection method is language independent.
- 1 March 2020
- Published by Elsevier in Pattern Recognition Letters
- Vol. 131, 213-218
Creating speaker independent ASR system through prosody modification based data augmentation
- 1 March 2020
- Published by Elsevier in Pattern Recognition Letters
- Vol. 131, 213-218
Creating speaker independent ASR system through prosody modification based data augmentation
- 1 October 2019
- Published by Elsevier in Digital Signal Processing
- Vol. 93, 34-42
Developing speaker independent ASR system using limited data through prosody modification based on fuzzy classification of spectral bins
- 1 October 2019
- Published by Elsevier in Digital Signal Processing
- Vol. 93, 34-42
Developing speaker independent ASR system using limited data through prosody modification based on fuzzy classification of spectral bins
- 24 April 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 27 (7) , 1189-1200
Detection of Nasalized Voiced Stops in Cleft Palate Speech Using Epoch-Synchronous Features
The presence of velopharyngeal dysfunction in individuals with cleft palate (CP) nasalizes the voiced stops. Due to this, voiced stops (/b/, /d/, /g/) tend to be perceive like nasal consonants (/m/, /n/, /ng/). In this work, a novel algorithm is proposed for the detection of nasalized voiced stops in CP speech using epoch-synchronous features. Speech regions corresponding to consonant and consonant-vowel transitions are segmented using the knowledge of glottal activity, syllable nucleus, low-frequency spectral dominance, and vowel onset point. The segmented regions are epoch-synchronously processed to analyze the spectral, spectro-temporal, excitation source, and periodicity characteristics of normal and nasalized voiced stops. Spectral and spectro-temporal features are computed using single pole filter based time-frequency representation. The amplitude of Hilbert envelope of linear prediction residual, measured around the epoch is used to analyze the effect of nasalization on excitation source. Comparison of speech frames of successive inter-epoch intervals is carried out to analyze the periodicity characteristics. The proposed features are used to develop a support vector machine classifier for the classification of normal and nasalized voiced stops. Segmentation accuracy for the proposed knowledge-based method is found to be better than the hidden Markov model based force-alignment approach. The detection rate of nasalized voiced stops is found to be high for the proposed epoch-synchronous features than the conventional Mel-frequency cepstral coefficients.
- 24 April 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 27 (7) , 1189-1200
Detection of Nasalized Voiced Stops in Cleft Palate Speech Using Epoch-Synchronous Features
The presence of velopharyngeal dysfunction in individuals with cleft palate (CP) nasalizes the voiced stops. Due to this, voiced stops (/b/, /d/, /g/) tend to be perceive like nasal consonants (/m/, /n/, /ng/). In this work, a novel algorithm is proposed for the detection of nasalized voiced stops in CP speech using epoch-synchronous features. Speech regions corresponding to consonant and consonant-vowel transitions are segmented using the knowledge of glottal activity, syllable nucleus, low-frequency spectral dominance, and vowel onset point. The segmented regions are epoch-synchronously processed to analyze the spectral, spectro-temporal, excitation source, and periodicity characteristics of normal and nasalized voiced stops. Spectral and spectro-temporal features are computed using single pole filter based time-frequency representation. The amplitude of Hilbert envelope of linear prediction residual, measured around the epoch is used to analyze the effect of nasalization on excitation source. Comparison of speech frames of successive inter-epoch intervals is carried out to analyze the periodicity characteristics. The proposed features are used to develop a support vector machine classifier for the classification of normal and nasalized voiced stops. Segmentation accuracy for the proposed knowledge-based method is found to be better than the hidden Markov model based force-alignment approach. The detection rate of nasalized voiced stops is found to be high for the proposed epoch-synchronous features than the conventional Mel-frequency cepstral coefficients.
- 26 February 2019
- Published by Springer Nature in Circuits, Systems, and Signal Processing
- Vol. 38 (10) , 4667-4682
Role of Linear, Mel and Inverse-Mel Filterbanks in Automatic Recognition of Speech from High-Pitched Speakers
- 26 February 2019
- Published by Springer Nature in Circuits, Systems, and Signal Processing
- Vol. 38 (10) , 4667-4682
Role of Linear, Mel and Inverse-Mel Filterbanks in Automatic Recognition of Speech from High-Pitched Speakers
- 3 December 2018
- Published by Springer Nature in International Journal of Speech Technology
- Vol. 22 (1) , 79-91
Speech synthesis for glottal activity region processing
- 3 December 2018
- Published by Springer Nature in International Journal of Speech Technology
- Vol. 22 (1) , 79-91
Speech synthesis for glottal activity region processing
- 1 August 2018
- Published by Elsevier in Digital Signal Processing
- Vol. 79, 142-151
Studying the role of pitch-adaptive spectral estimation and speaking-rate normalization in automatic speech recognition
- 1 August 2018
- Published by Elsevier in Digital Signal Processing
- Vol. 79, 142-151
Studying the role of pitch-adaptive spectral estimation and speaking-rate normalization in automatic speech recognition
- 1 July 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4, 100-104
Detecting Developmental Dysphasia in Children using Speech Data
Developmental dysphasia or specific language impairment (SLI) is a disorder that is known to delay the process of acquiring language skills in children without other disabilities. Approximately 5-7% of children in kindergarten group are affected with SLI as reported in literature. Boys are more prone to be affected by this disorder compared to girls. In this paper, we present our preliminary attempts towards detecting SLI in children using their speech data. In this regard, we have used Mel-frequency cepstral coefficients (MFCC) for front-end speech parameterization. We have also presented an analysis to show how MFCC features help in discriminating the healthy children from those affected with SLI. The MFCC feature vectors are then used to develop two-class classifiers for discriminating healthy children from those suffering from SLI. The said two-class classifiers are developed using extreme learning machine (ELM) trained and tested on speech data collected from healthy children as well as those affected with SLI. ELM are fast to train and are known to be quite effective even when the training data is sparse. For extracting utterance-level features to be given as input to the ELM, Gaussian posteriograms learned on frame-level acoustic features are used. Several different types of ELMs are explored in this work and the kernel ELM is noted to outperform the rest with an accuracy of 99.41%.
- 1 July 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4, 100-104
Detecting Developmental Dysphasia in Children using Speech Data
Developmental dysphasia or specific language impairment (SLI) is a disorder that is known to delay the process of acquiring language skills in children without other disabilities. Approximately 5-7% of children in kindergarten group are affected with SLI as reported in literature. Boys are more prone to be affected by this disorder compared to girls. In this paper, we present our preliminary attempts towards detecting SLI in children using their speech data. In this regard, we have used Mel-frequency cepstral coefficients (MFCC) for front-end speech parameterization. We have also presented an analysis to show how MFCC features help in discriminating the healthy children from those affected with SLI. The MFCC feature vectors are then used to develop two-class classifiers for discriminating healthy children from those suffering from SLI. The said two-class classifiers are developed using extreme learning machine (ELM) trained and tested on speech data collected from healthy children as well as those affected with SLI. ELM are fast to train and are known to be quite effective even when the training data is sparse. For extracting utterance-level features to be given as input to the ELM, Gaussian posteriograms learned on frame-level acoustic features are used. Several different types of ELMs are explored in this work and the kernel ELM is noted to outperform the rest with an accuracy of 99.41%.
- 1 April 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5674-5678
ON the Use of Wavenet as a Statistical Vocoder
In this paper, we explore the possibility of using the WaveNet architecture as a statistical vocoder. In that case, the generation of speech waveforms is locally conditioned only by acoustic features. Focusing on the single speaker case at the moment, we investigate the impact of the local conditions as well as that of the amount of data available for training. Furthermore, variations of the WaveNet architecture are considered and discussed in the context of our work. We compare our work against a very recent work which also used WaveNet architecture as a speech vocoder using the same speech data. More specifically, we used two female and two male speakers from the CMU-ARCTIC database to contrast the use of cepstrum coefficients and filter-bank features as local conditioners with the goal to improve the overall quality for both male and female speakers. In the paper we also discuss the impact of the size of the training data. Objective metrics for quality and intelligibility of the generated by the WaveNet speech as well as subjective tests support our suggestions.
- 1 April 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5674-5678
ON the Use of Wavenet as a Statistical Vocoder
In this paper, we explore the possibility of using the WaveNet architecture as a statistical vocoder. In that case, the generation of speech waveforms is locally conditioned only by acoustic features. Focusing on the single speaker case at the moment, we investigate the impact of the local conditions as well as that of the amount of data available for training. Furthermore, variations of the WaveNet architecture are considered and discussed in the context of our work. We compare our work against a very recent work which also used WaveNet architecture as a speech vocoder using the same speech data. More specifically, we used two female and two male speakers from the CMU-ARCTIC database to contrast the use of cepstrum coefficients and filter-bank features as local conditioners with the goal to improve the overall quality for both male and female speakers. In the paper we also discuss the impact of the size of the training data. Objective metrics for quality and intelligibility of the generated by the WaveNet speech as well as subjective tests support our suggestions.