Cristian Tejedor-Garcia

Simone Wills, Yu Bai, Cristian Tejedor-Garcia et al.

Voicebots have provided a new avenue for supporting the development of language skills, particularly within the context of second language learning. Voicebots, though, have largely been geared towards native adult speakers. We sought to assess the performance of two state-of-the-art ASR systems, Wav2Vec2.0 and Whisper AI, with a view to developing a voicebot that can support children acquiring a foreign language. We evaluated their performance on read and extemporaneous speech of native and non-native Dutch children. We also investigated the utility of using ASR technology to provide insight into the children's pronunciation and fluency. The results show that recent, pre-trained ASR transformer-based models achieve acceptable performance from which detailed feedback on phoneme pronunciation quality can be extracted, despite the challenging nature of child and non-native speech.

Lucía Gómez-Zaragozá, Simone Wills, Cristian Tejedor-Garcia et al.

Alzheimer's Disease (AD) is the world's leading neurodegenerative disease, which often results in communication difficulties. Analysing speech can serve as a diagnostic tool for identifying the condition. The recent ADReSS challenge provided a dataset for AD classification and highlighted the utility of manual transcriptions. In this study, we used the new state-of-the-art Automatic Speech Recognition (ASR) model Whisper to obtain the transcriptions, which also include automatic punctuation. The classification models achieved test accuracy scores of 0.854 and 0.833 combining the pretrained FastText word embeddings and recurrent neural networks on manual and ASR transcripts respectively. Additionally, we explored the influence of including pause information and punctuation in the transcriptions. We found that punctuation only yielded minor improvements in some cases, whereas pause encoding aided AD classification for both manual and ASR transcriptions across all approaches investigated.

Bo Molenaar, Cristian Tejedor-Garcia, Helmer Strik et al.

Automatic assessment of reading fluency using automatic speech recognition (ASR) holds great potential for early detection of reading difficulties and subsequent timely intervention. Precise assessment tools are required, especially for languages other than English. In this study, we evaluate six state-of-the-art ASR-based systems for automatically assessing Dutch oral reading accuracy using Kaldi and Whisper. Results show our most successful system reached substantial agreement with human evaluations (MCC = .63). The same system reached the highest correlation between forced decoding confidence scores and word correctness (r = .45). This system's language model (LM) consisted of manual orthographic transcriptions and reading prompts of the test data, which shows that including reading errors in the LM improves assessment performance. We discuss the implications for developing automatic assessment systems and identify possible avenues of future research.

Yu Bai, Cristian Tejedor-Garcia, Ferdy Hubers et al.

The interest in employing automatic speech recognition (ASR) in applications for reading practice has been growing in recent years. In a previous study, we presented an ASR-based Dutch reading tutor application that was developed to provide instantaneous feedback to first-graders learning to read. We saw that ASR has potential at this stage of the reading process, as the results suggested that pupils made progress in reading accuracy and fluency by using the software. In the current study, we used children's speech from an existing corpus (JASMIN) to develop two new ASR systems, and compared the results to those of the previous study. We analyze correct/incorrect classification of the ASR systems using human transcripts at word level, by means of evaluation measures such as Cohen's Kappa, Matthews Correlation Coefficient (MCC), precision, recall and F-measures. We observe improvements for the newly developed ASR systems regarding the agreement with human-based judgment and correct rejection (CR). The accuracy of the ASR systems varies for different reading tasks and word types. Our results suggest that, in the current configuration, it is difficult to classify isolated words. We discuss these results, possible ways to improve our systems and avenues for future research.

Aditya Kamlesh Parikh, Cristian Tejedor-Garcia, Catia Cucchiarini et al.

Reliable and interpretable automated assessment of second-language (L2) speech remains a central challenge, as large speech-language models (SpeechLLMs) often struggle to align with the nuanced variability of human raters. To address this, we introduce a rubric-guided reasoning framework that explicitly encodes multi-aspect human assessment criteria: accuracy, fluency, and prosody, while calibrating model uncertainty to capture natural rating variability. We fine-tune the Qwen2-Audio-7B-Instruct model using multi-rater human judgments and develop an uncertainty-calibrated regression approach supported by conformal calibration for interpretable confidence intervals. Our Gaussian uncertainty modeling and conformal calibration approach achieves the strongest alignment with human ratings, outperforming regression and classification baselines. The model reliably assesses fluency and prosody while highlighting the inherent difficulty of assessing accuracy. Together, these results demonstrate that rubric-guided, uncertainty-calibrated reasoning offers a principled path toward trustworthy and explainable SpeechLLM-based speech assessment.

Terry Yi Zhong, Cristian Tejedor-Garcia, Khiet P. Truong et al.

Early-stage Parkinson's disease (EarlyPD) detection from speech is clinically meaningful yet underexplored, and published results are hard to compare because studies differ in datasets, languages, tasks, evaluation protocols, and EarlyPD definitions. To address this issue, we propose the first benchmark for speech-based EarlyPD detection, with a speaker-independent split designed for fair and replicable cross-method evaluation on researcher-accessible datasets. The benchmark covers three common speech tasks and evaluates methods under different training-resource settings. We also present multi-dimensional evaluation breakdowns by dataset, aggregation level, gender, and disease stage to support fine-grained comparisons and clinical adoption. Our results provide a replicable reference and actionable insights, encouraging the adoption of this publicly available benchmark to advance robust and clinically meaningful EarlyPD detection from speech.

Mehtab Ur Rahman, Martha Larson, Cristian Tejedor-Garcia

Voice privacy approaches that preserve the anonymity of speakers modify speech in an attempt to break the link with the true identity of the speaker. Current benchmarks measure speaker protection based on signal-to-signal comparisons. In this paper, we introduce an attribute-based perspective, where we measure privacy protection in terms of comparisons between sets of speaker attributes. First, we analyze privacy impact by calculating speaker uniqueness for ground truth attributes, attributes inferred on the original speech, and attributes inferred on speech protected with standard anonymization. Next, we examine a threat scenario involving only a single utterance per speaker and calculate attack error rates. Overall, we observe that inferred attributes still present a risk despite attribute inference errors. Our research points to the importance of considering both attribute-related threats and protection mechanisms in future voice privacy research.

Terry Yi Zhong, Esther Janse, Cristian Tejedor-Garcia et al.

Speech-based Parkinson's disease (PD) detection has gained attention for its automated, cost-effective, and non-intrusive nature. As research studies usually rely on data from diagnostic-oriented speech tasks, this work explores the feasibility of diagnosing PD on the basis of speech data not originally intended for diagnostic purposes, using the Turn-Taking (TT) dataset. Our findings indicate that TT can be as useful as diagnostic-oriented PD datasets like PC-GITA. We also investigate which specific dataset characteristics impact PD classification performance. The results show that concatenating audio recordings and balancing participants' gender and status distributions can be beneficial. Cross-dataset evaluation reveals that models trained on PC-GITA generalize poorly to TT, whereas models trained on TT perform better on PC-GITA. Furthermore, we provide insights into the high variability across folds, which is mainly due to large differences in individual speaker performance.

Terry Yi Zhong, Cristian Tejedor-Garcia, Martha Larson et al.

Parkinson's Disease (PD) affects over 10 million people globally, with speech impairments often preceding motor symptoms by years, making speech a valuable modality for early, non-invasive detection. While recent deep-learning models achieve high accuracy, they typically lack the explainability required for clinical use. To address this, we propose RECA-PD, a novel, robust, and explainable cross-attention architecture that combines interpretable speech features with self-supervised representations. RECA-PD matches state-of-the-art performance in Speech-based PD detection while providing explanations that are more consistent and more clinically meaningful. Additionally, we demonstrate that performance degradation in certain speech tasks (e.g., monologue) can be mitigated by segmenting long recordings. Our findings indicate that performance and explainability are not necessarily mutually exclusive. Future work will enhance the usability of explanations for non-experts and explore severity estimation to increase the real-world clinical relevance.

Lingyun Gao, Cristian Tejedor-Garcia, Catia Cucchiarini et al.

Automatic reading aloud evaluation can provide valuable support to teachers by enabling more efficient scoring of reading exercises. However, research on reading evaluation systems and applications remains limited. We present a novel multimodal approach that leverages audio and knowledge from text resources. In particular, we explored the potential of using Whisper and instruction-tuned large language models (LLMs) with prompts to improve transcriptions for child speech recognition, as well as their effectiveness in downstream reading mistake detection. Our results demonstrate the effectiveness of prompting Whisper and prompting LLM, compared to the baseline Whisper model without prompting. The best performing system achieved state-of-the-art recognition performance in Dutch child read speech, with a word error rate (WER) of 5.1%, improving the baseline WER of 9.4%. Furthermore, it significantly improved reading mistake detection, increasing the F1 score from 0.39 to 0.73.

Aditya Kamlesh Parikh, Cristian Tejedor-Garcia, Catia Cucchiarini et al.

Computer-Assisted Pronunciation Training (CAPT) systems employ automatic measures of pronunciation quality, such as the goodness of pronunciation (GOP) metric. GOP relies on forced alignments, which are prone to labeling and segmentation errors due to acoustic variability. While alignment-free methods address these challenges, they are computationally expensive and scale poorly with phoneme sequence length and inventory size. To enhance efficiency, we introduce a substitution-aware alignment-free GOP that restricts phoneme substitutions based on phoneme clusters and common learner errors. We evaluated our GOP on two L2 English speech datasets, one with child speech, My Pronunciation Coach (MPC), and SpeechOcean762, which includes child and adult speech. We compared RPS (restricted phoneme substitutions) and UPS (unrestricted phoneme substitutions) setups within alignment-free methods, which outperformed the baseline. We discuss our results and outline avenues for future research.

Aditya Kamlesh Parikh, Cristian Tejedor-Garcia, Catia Cucchiarini et al.

Pronunciation assessment relies on goodness of pronunciation (GOP) scores, traditionally derived from softmax-based posterior probabilities. However, posterior probabilities may suffer from overconfidence and poor phoneme separation, limiting their effectiveness. This study compares logit-based GOP scores with probability-based GOP scores for mispronunciation detection. We conducted our experiment on two L2 English speech datasets spoken by Dutch and Mandarin speakers, assessing classification performance and correlation with human ratings. Logit-based methods outperform probability-based GOP in classification, but their effectiveness depends on dataset characteristics. The maximum logit GOP shows the strongest alignment with human perception, while a combination of different GOP scores balances probability and logit features. The findings suggest that hybrid GOP methods incorporating uncertainty modeling and phoneme-specific weighting improve pronunciation assessment.

Emmy Postma, Cristian Tejedor-Garcia

Speech impairments are prevalent biomarkers for Parkinson's Disease (PD), motivating the development of diagnostic techniques using speech data for clinical applications. Although deep acoustic features have shown promise for PD classification, their effectiveness often varies due to individual speaker differences, a factor that has not been thoroughly explored in the existing literature. This study investigates the effectiveness of three pre-trained audio embeddings (OpenL3, VGGish and Wav2Vec2.0 models) for PD classification. Using the NeuroVoz dataset, OpenL3 outperforms others in diadochokinesis (DDK) and listen and repeat (LR) tasks, capturing critical acoustic features for PD detection. Only Wav2Vec2.0 shows significant gender bias, achieving more favorable results for male speakers, in DDK tasks. The misclassified cases reveal challenges with atypical speech patterns, highlighting the need for improved feature extraction and model robustness in PD detection.

Lingyun Gao, Cristian Tejedor-Garcia, Helmer Strik et al.

Automatic reading diagnosis systems can benefit both teachers for more efficient scoring of reading exercises and students for accessing reading exercises with feedback more easily. However, there are limited studies on Automatic Speech Recognition (ASR) for child speech in languages other than English, and limited research on ASR-based reading diagnosis systems. This study investigates how efficiently state-of-the-art (SOTA) pretrained ASR models recognize Dutch native children speech and manage to detect reading miscues. We found that Hubert Large finetuned on Dutch speech achieves SOTA phoneme-level child speech recognition (PER at 23.1\%), while Whisper (Faster Whisper Large-v2) achieves SOTA word-level performance (WER at 9.8\%). Our findings suggest that Wav2Vec2 Large and Whisper are the two best ASR models for reading miscue detection. Specifically, Wav2Vec2 Large shows the highest recall at 0.83, whereas Whisper exhibits the highest precision at 0.52 and an F1 score of 0.52.