Sudarsana Reddy Kadiri

Dhananjaya Gowda, Sudarsana Reddy Kadiri, Brad Story et al.

In this paper, we propose a new method for the accurate estimation and tracking of formants in speech signals using time-varying quasi-closed-phase (TVQCP) analysis. Conventional formant tracking methods typically adopt a two-stage estimate-and-track strategy wherein an initial set of formant candidates are estimated using short-time analysis (e.g., 10--50 ms), followed by a tracking stage based on dynamic programming or a linear state-space model. One of the main disadvantages of these approaches is that the tracking stage, however good it may be, cannot improve upon the formant estimation accuracy of the first stage. The proposed TVQCP method provides a single-stage formant tracking that combines the estimation and tracking stages into one. TVQCP analysis combines three approaches to improve formant estimation and tracking: (1) it uses temporally weighted quasi-closed-phase analysis to derive closed-phase estimates of the vocal tract with reduced interference from the excitation source, (2) it increases the residual sparsity by using the $L_1$ optimization and (3) it uses time-varying linear prediction analysis over long time windows (e.g., 100--200 ms) to impose a continuity constraint on the vocal tract model and hence on the formant trajectories. Formant tracking experiments with a wide variety of synthetic and natural speech signals show that the proposed TVQCP method performs better than conventional and popular formant tracking tools, such as Wavesurfer and Praat (based on dynamic programming), the KARMA algorithm (based on Kalman filtering), and DeepFormants (based on deep neural networks trained in a supervised manner). Matlab scripts for the proposed method can be found at: https://github.com/njaygowda/ftrack

Sudarsana Reddy Kadiri, Paavo Alku

Automatic detection of voice pathology enables objective assessment and earlier intervention for the diagnosis. This study provides a systematic analysis of glottal source features and investigates their effectiveness in voice pathology detection. Glottal source features are extracted using glottal flows estimated with the quasi-closed phase (QCP) glottal inverse filtering method, using approximate glottal source signals computed with the zero frequency filtering (ZFF) method, and using acoustic voice signals directly. In addition, we propose to derive mel-frequency cepstral coefficients (MFCCs) from the glottal source waveforms computed by QCP and ZFF to effectively capture the variations in glottal source spectra of pathological voice. Experiments were carried out using two databases, the Hospital Universitario Principe de Asturias (HUPA) database and the Saarbrucken Voice Disorders (SVD) database. Analysis of features revealed that the glottal source contains information that discriminates normal and pathological voice. Pathology detection experiments were carried out using support vector machine (SVM). From the detection experiments it was observed that the performance achieved with the studied glottal source features is comparable or better than that of conventional MFCCs and perceptual linear prediction (PLP) features. The best detection performance was achieved when the glottal source features were combined with the conventional MFCCs and PLP features, which indicates the complementary nature of the features.

Farhad Javanmardi, Saska Tirronen, Manila Kodali et al.

Automatic detection and severity level classification of dysarthria directly from acoustic speech signals can be used as a tool in medical diagnosis. In this work, the pre-trained wav2vec 2.0 model is studied as a feature extractor to build detection and severity level classification systems for dysarthric speech. The experiments were carried out with the popularly used UA-speech database. In the detection experiments, the results revealed that the best performance was obtained using the embeddings from the first layer of the wav2vec model that yielded an absolute improvement of 1.23% in accuracy compared to the best performing baseline feature (spectrogram). In the studied severity level classification task, the results revealed that the embeddings from the final layer gave an absolute improvement of 10.62% in accuracy compared to the best baseline features (mel-frequency cepstral coefficients).

Sudarsana Reddy Kadiri, Farhad Javanmardi, Paavo Alku

Prior studies in the automatic classification of voice quality have mainly studied the use of the acoustic speech signal as input. Recently, a few studies have been carried out by jointly using both speech and neck surface accelerometer (NSA) signals as inputs, and by extracting MFCCs and glottal source features. This study examines simultaneously-recorded speech and NSA signals in the classification of voice quality (breathy, modal, and pressed) using features derived from three self-supervised pre-trained models (wav2vec2-BASE, wav2vec2-LARGE, and HuBERT) and using a SVM as well as CNNs as classifiers. Furthermore, the effectiveness of the pre-trained models is compared in feature extraction between glottal source waveforms and raw signal waveforms for both speech and NSA inputs. Using two signal processing methods (quasi-closed phase (QCP) glottal inverse filtering and zero frequency filtering (ZFF)), glottal source waveforms are estimated from both speech and NSA signals. The study has three main goals: (1) to study whether features derived from pre-trained models improve classification accuracy compared to conventional features (spectrogram, mel-spectrogram, MFCCs, i-vector, and x-vector), (2) to investigate which of the two modalities (speech vs. NSA) is more effective in the classification task with pre-trained model-based features, and (3) to evaluate whether the deep learning-based CNN classifier can enhance the classification accuracy in comparison to the SVM classifier. The results revealed that the use of the NSA input showed better classification performance compared to the speech signal. Between the features, the pre-trained model-based features showed better classification accuracies, both for speech and NSA inputs compared to the conventional features. It was also found that the HuBERT features performed better than the wav2vec2-BASE and wav2vec2-LARGE features.

Paavo Alku, Sudarsana Reddy Kadiri, Dhananjaya Gowda

In this study, formant tracking is investigated by refining the formants tracked by an existing data-driven tracker, DeepFormants, using the formants estimated in a model-driven manner by linear prediction (LP)-based methods. As LP-based formant estimation methods, conventional covariance analysis (LP-COV) and the recently proposed quasi-closed phase forward-backward (QCP-FB) analysis are used. In the proposed refinement approach, the contours of the three lowest formants are first predicted by the data-driven DeepFormants tracker, and the predicted formants are replaced frame-wise with local spectral peaks shown by the model-driven LP-based methods. The refinement procedure can be plugged into the DeepFormants tracker with no need for any new data learning. Two refined DeepFormants trackers were compared with the original DeepFormants and with five known traditional trackers using the popular vocal tract resonance (VTR) corpus. The results indicated that the data-driven DeepFormants trackers outperformed the conventional trackers and that the best performance was obtained by refining the formants predicted by DeepFormants using QCP-FB analysis. In addition, by tracking formants using VTR speech that was corrupted by additive noise, the study showed that the refined DeepFormants trackers were more resilient to noise than the reference trackers. In general, these results suggest that LP-based model-driven approaches, which have traditionally been used in formant estimation, can be combined with a modern data-driven tracker easily with no further training to improve the tracker's performance.

Sudarsana Reddy Kadiri, Manila Kodali, Paavo Alku

Developing objective methods for assessing the severity of Parkinson's disease (PD) is crucial for improving the diagnosis and treatment. This study proposes two sets of novel features derived from the single frequency filtering (SFF) method: (1) SFF cepstral coefficients (SFFCC) and (2) MFCCs from the SFF (MFCC-SFF) for the severity classification of PD. Prior studies have demonstrated that SFF offers greater spectro-temporal resolution compared to the short-time Fourier transform. The study uses the PC-GITA database, which includes speech of PD patients and healthy controls produced in three speaking tasks (vowels, sentences, text reading). Experiments using the SVM classifier revealed that the proposed features outperformed the conventional MFCCs in all three speaking tasks. The proposed SFFCC and MFCC-SFF features gave a relative improvement of 5.8% and 2.3% for the vowel task, 7.0% & 1.8% for the sentence task, and 2.4% and 1.1% for the read text task, in comparison to MFCC features.

Liangyu Nie, Sudarsana Reddy Kadiri, Ruchit Agrawal

Stuttering is a common speech impediment that is caused by irregular disruptions in speech production, affecting over 70 million people across the world. Standard automatic speech processing tools do not take speech ailments into account and are thereby not able to generate meaningful results when presented with stuttered speech as input. The automatic detection of stuttering is an integral step towards building efficient, context-aware speech processing systems. While previous approaches explore both statistical and neural approaches for stuttering detection, all of these methods are uni-modal in nature. This paper presents MMSD-Net, the first multi-modal neural framework for stuttering detection. Experiments and results demonstrate that incorporating the visual signal significantly aids stuttering detection, and our model yields an improvement of 2-17% in the F1-score over existing state-of-the-art uni-modal approaches.

Aditya Ashvin, Rimita Lahiri, Aditya Kommineni et al.

Reliable transcription of child-adult conversations in clinical settings is crucial for diagnosing developmental disorders like Autism. Recent advances in deep learning and availability of large scale transcribed data has led to development of speech foundation models that have shown dramatic improvements in ASR performance. However, their performance on conversational child-adult interactions remains underexplored. In this work, we provide a comprehensive evaluation of ASR performance on a dataset containing child-adult interactions from autism diagnostic sessions, using Whisper, Wav2Vec2, HuBERT, and WavLM. We find that speech foundation models show a noticeable performance drop (15-20% absolute WER) for child speech compared to adult speech in the conversational setting. Then, we fine-tune the best-performing zero-shot model (Whisper-large) using LoRA in a low-resource setting, yielding 8% and 13% absolute WER improvements for child and adult speech, respectively.

Sean Foley, Hong Nguyen, Jihwan Lee et al.

Although many previous studies have carried out multimodal learning with real-time MRI data that captures the audio-visual kinematics of the vocal tract during speech, these studies have been limited by their reliance on multi-speaker corpora. This prevents such models from learning a detailed relationship between acoustics and articulation due to considerable cross-speaker variability. In this study, we develop unimodal audio and video models as well as multimodal models for phoneme recognition using a long-form single-speaker MRI corpus, with the goal of disentangling and interpreting the contributions of each modality. Audio and multimodal models show similar performance on different phonetic manner classes but diverge on places of articulation. Interpretation of the models' latent space shows similar encoding of the phonetic space across audio and multimodal models, while the models' attention weights highlight differences in acoustic and articulatory timing for certain phonemes.

Jihwan Lee, Tiantian Feng, Aditya Kommineni et al.

Brain-computer interfaces (BCI) offer numerous human-centered application possibilities, particularly affecting people with neurological disorders. Text or speech decoding from brain activities is a relevant domain that could augment the quality of life for people with impaired speech perception. We propose a novel approach to enhance listened speech decoding from electroencephalography (EEG) signals by utilizing an auxiliary phoneme predictor that simultaneously decodes textual phoneme sequences. The proposed model architecture consists of three main parts: EEG module, speech module, and phoneme predictor. The EEG module learns to properly represent EEG signals into EEG embeddings. The speech module generates speech waveforms from the EEG embeddings. The phoneme predictor outputs the decoded phoneme sequences in text modality. Our proposed approach allows users to obtain decoded listened speech from EEG signals in both modalities (speech waveforms and textual phoneme sequences) simultaneously, eliminating the need for a concatenated sequential pipeline for each modality. The proposed approach also outperforms previous methods in both modalities. The source code and speech samples are publicly available.

Jihwan Lee, Parsa Razmara, Kevin Huang et al.

Speech production is a complex process spanning neural planning, motor control, muscle activation, and articulatory kinematics. While the acoustic speech signal is the most accessible product of the speech production act, it does not directly reveal its causal neurophysiological substrates. We present the first simultaneous acquisition of real-time (dynamic) MRI, EEG, and surface EMG, capturing several key aspects of the speech production chain: brain signals, muscle activations, and articulatory movements. This multimodal acquisition paradigm presents substantial technical challenges, including MRI-induced electromagnetic interference and myogenic artifacts. To mitigate these, we introduce an artifact suppression pipeline tailored to this tri-modal setting. Once fully developed, this framework is poised to offer an unprecedented window into speech neuroscience and insights leading to brain-computer interface advances.

Subham Kutum, Abhijit Sinha, Hemant Kumar Kathania et al.

Numerous methods have been proposed to enhance Keyword Spotting (KWS) in adult speech, but children's speech presents unique challenges for KWS systems due to its distinct acoustic and linguistic characteristics. This paper introduces a zero-shot KWS approach that leverages state-of-the-art self-supervised learning (SSL) models, including Wav2Vec2, HuBERT and Data2Vec. Features are extracted layer-wise from these SSL models and used to train a Kaldi-based DNN KWS system. The WSJCAM0 adult speech dataset was used for training, while the PFSTAR children's speech dataset was used for testing, demonstrating the zero-shot capability of our method. Our approach achieved state-of-the-art results across all keyword sets for children's speech. Notably, the Wav2Vec2 model, particularly layer 22, performed the best, delivering an ATWV score of 0.691, a MTWV score of 0.7003 and probability of false alarm and probability of miss of 0.0164 and 0.0547 respectively, for a set of 30 keywords. Furthermore, age-specific performance evaluation confirmed the system's effectiveness across different age groups of children. To assess the system's robustness against noise, additional experiments were conducted using the best-performing layer of the best-performing Wav2Vec2 model. The results demonstrated a significant improvement over traditional MFCC-based baseline, emphasizing the potential of SSL embeddings even in noisy conditions. To further generalize the KWS framework, the experiments were repeated for an additional CMU dataset. Overall the results highlight the significant contribution of SSL features in enhancing Zero-Shot KWS performance for children's speech, effectively addressing the challenges associated with the distinct characteristics of child speakers.

Abhijit Sinha, Hemant Kumar Kathania, Sudarsana Reddy Kadiri et al.

Automatic Speech Recognition (ASR) systems often struggle to accurately process children's speech due to its distinct and highly variable acoustic and linguistic characteristics. While recent advancements in self-supervised learning (SSL) models have greatly enhanced the transcription of adult speech, accurately transcribing children's speech remains a significant challenge. This study investigates the effectiveness of layer-wise features extracted from state-of-the-art SSL pre-trained models - specifically, Wav2Vec2, HuBERT, Data2Vec, and WavLM in improving the performance of ASR for children's speech in zero-shot scenarios. A detailed analysis of features extracted from these models was conducted, integrating them into a simplified DNN-based ASR system using the Kaldi toolkit. The analysis identified the most effective layers for enhancing ASR performance on children's speech in a zero-shot scenario, where WSJCAM0 adult speech was used for training and PFSTAR children speech for testing. Experimental results indicated that Layer 22 of the Wav2Vec2 model achieved the lowest Word Error Rate (WER) of 5.15%, representing a 51.64% relative improvement over the direct zero-shot decoding using Wav2Vec2 (WER of 10.65%). Additionally, age group-wise analysis demonstrated consistent performance improvements with increasing age, along with significant gains observed even in younger age groups using the SSL features. Further experiments on the CMU Kids dataset confirmed similar trends, highlighting the generalizability of the proposed approach.

Abhijit Sinha, Harishankar Kumar, Mohit Joshi et al.

Children's speech presents challenges for age and gender classification due to high variability in pitch, articulation, and developmental traits. While self-supervised learning (SSL) models perform well on adult speech tasks, their ability to encode speaker traits in children remains underexplored. This paper presents a detailed layer-wise analysis of four Wav2Vec2 variants using the PFSTAR and CMU Kids datasets. Results show that early layers (1-7) capture speaker-specific cues more effectively than deeper layers, which increasingly focus on linguistic information. Applying PCA further improves classification, reducing redundancy and highlighting the most informative components. The Wav2Vec2-large-lv60 model achieves 97.14% (age) and 98.20% (gender) on CMU Kids; base-100h and large-lv60 models reach 86.05% and 95.00% on PFSTAR. These results reveal how speaker traits are structured across SSL model depth and support more targeted, adaptive strategies for child-aware speech interfaces.

Anne-Maria Laukkanen, Sudarsana Reddy Kadiri, Shrikanth Narayanan et al.

Objectives: ncreased prevalence of social creak particularly among female speakers has been reported in several studies. The study of social creak has been previously conducted by combining perceptual evaluation of speech with conventional acoustical parameters such as the harmonic-to-noise ratio and cepstral peak prominence. In the current study, machine learning (ML) was used to automatically distinguish speech of low amount of social creak from speech of high amount of social creak. Methods: The amount of creak in continuous speech samples produced in Finnish by 90 female speakers was first perceptually assessed by two voice specialists. Based on their assessments, the speech samples were divided into two categories (low $vs$. high amount of creak). Using the speech signals and their creak labels, seven different ML models were trained. Three spectral representations were used as feature for each model. Results: The results show that the best performance (accuracy of 71.1\%) was obtained by the following two systems: an Adaboost classifier using the mel-spectrogram feature and a decision tree classifier using the mel-frequency cepstral coefficient feature. Conclusions: The study of social creak is becoming increasingly popular in sociolinguistic and vocological research. The conventional human perceptual assessment of the amount of creak is laborious and therefore ML technology could be used to assist researchers studying social creak. The classification systems reported in this study could be considered as baselines in future ML-based studies on social creak.

Dhananjaya Gowda, Bajibabu Bollepalli, Sudarsana Reddy Kadiri et al.

Formant tracking is investigated in this study by using trackers based on dynamic programming (DP) and deep neural nets (DNNs). Using the DP approach, six formant estimation methods were first compared. The six methods include linear prediction (LP) algorithms, weighted LP algorithms and the recently developed quasi-closed phase forward-backward (QCP-FB) method. QCP-FB gave the best performance in the comparison. Therefore, a novel formant tracking approach, which combines benefits of deep learning and signal processing based on QCP-FB, was proposed. In this approach, the formants predicted by a DNN-based tracker from a speech frame are refined using the peaks of the all-pole spectrum computed by QCP-FB from the same frame. Results show that the proposed DNN-based tracker performed better both in detection rate and estimation error for the lowest three formants compared to reference formant trackers. Compared to the popular Wavesurfer, for example, the proposed tracker gave a reduction of 29%, 48% and 35% in the estimation error for the lowest three formants, respectively.

Tamás Grósz, Mittul Singh, Sudarsana Reddy Kadiri et al.

End-to-end neural network models (E2E) have shown significant performance benefits on different INTERSPEECH ComParE tasks. Prior work has applied either a single instance of an E2E model for a task or the same E2E architecture for different tasks. However, applying a single model is unstable or using the same architecture under-utilizes task-specific information. On ComParE 2020 tasks, we investigate applying an ensemble of E2E models for robust performance and developing task-specific modifications for each task. ComParE 2020 introduces three sub-challenges: the breathing sub-challenge to predict the output of a respiratory belt worn by a patient while speaking, the elderly sub-challenge to estimate the elderly speaker's arousal and valence levels and the mask sub-challenge to classify if the speaker is wearing a mask or not. On each of these tasks, an ensemble outperforms the single E2E model. On the breathing sub-challenge, we study the impact of multi-loss strategies on task performance. On the elderly sub-challenge, predicting the valence and arousal levels prompts us to investigate multi-task training and implement data sampling strategies to handle class imbalance. On the mask sub-challenge, using an E2E system without feature engineering is competitive to feature-engineered baselines and provides substantial gains when combined with feature-engineered baselines.