Thanathai Lertpetchpun

Shih-Heng Wang, Tiantian Feng, Aditya Kommineni et al.

Neural Audio Codecs (NACs) are widely adopted in modern speech systems, yet how they encode linguistic and paralinguistic information remains unclear. Improving the interpretability of NAC representations is critical for understanding and deploying them in sensitive applications. Hence, we employ Sparse Autoencoders (SAEs) to decompose dense NAC representations into sparse, interpretable activations. In this work, we focus on a challenging paralinguistic attribute-accent-and propose a framework to quantify NAC interpretability. We evaluate four NAC models under 16 SAE configurations using a relative performance index. Our results show that DAC and SpeechTokenizer achieve the highest interpretability. We further reveal that acoustic-oriented NACs encode accent information primarily in activation magnitudes of sparse representations, whereas phonetic-oriented NACs rely more on activation positions, and that low-bitrate EnCodec variants show higher interpretability.

Tiantian Feng, Kevin Huang, Anfeng Xu et al.

We present Voxlect, a novel benchmark for modeling dialects and regional languages worldwide using speech foundation models. Specifically, we report comprehensive benchmark evaluations on dialects and regional language varieties in English, Arabic, Mandarin and Cantonese, Tibetan, Indic languages, Thai, Spanish, French, German, Brazilian Portuguese, and Italian. Our study used over 2 million training utterances from 30 publicly available speech corpora that are provided with dialectal information. We evaluate the performance of several widely used speech foundation models in classifying speech dialects. We assess the robustness of the dialectal models under noisy conditions and present an error analysis that highlights modeling results aligned with geographic continuity. In addition to benchmarking dialect classification, we demonstrate several downstream applications enabled by Voxlect. Specifically, we show that Voxlect can be applied to augment existing speech recognition datasets with dialect information, enabling a more detailed analysis of ASR performance across dialectal variations. Voxlect is also used as a tool to evaluate the performance of speech generation systems. Voxlect is publicly available with the license of the RAIL family at: https://github.com/tiantiaf0627/voxlect.

Jordan Prescott, Thanathai Lertpetchpun, Shrikanth Narayanan

Adversarial perturbations exploit vulnerabilities in automatic speech recognition (ASR) systems while preserving human perceived linguistic content. Neural audio codecs impose a discrete bottleneck that can suppress fine-grained signal variations associated with adversarial noise. We examine how the granularity of this bottleneck, controlled by residual vector quantization (RVQ) depth, shapes adversarial robustness. We observe a non-monotonic trade-off under gradient-based attacks: shallow quantization suppresses adversarial perturbations but degrades speech content, while deeper quantization preserves both content and perturbations. Intermediate depths balance these effects and minimize transcription error. We further show that adversarially induced changes in discrete codebook tokens strongly correlate with transcription error. These gains persist under adaptive attacks, where neural codec configurations outperform traditional compression defenses.

Thanathai Lertpetchpun, Yoonjeong Lee, Thanapat Trachu et al.

Many spoken languages, including English, exhibit wide variation in dialects and accents, making accent control an important capability for flexible text-to-speech (TTS) models. Current TTS systems typically generate accented speech by conditioning on speaker embeddings associated with specific accents. While effective, this approach offers limited interpretability and controllability, as embeddings also encode traits such as timbre and emotion. In this study, we analyze the interaction between speaker embeddings and linguistically motivated phonological rules in accented speech synthesis. Using American and British English as a case study, we implement rules for flapping, rhoticity, and vowel correspondences. We propose the phoneme shift rate (PSR), a novel metric quantifying how strongly embeddings preserve or override rule-based transformations. Experiments show that combining rules with embeddings yields more authentic accents, while embeddings can attenuate or overwrite rules, revealing entanglement between accent and speaker identity. Our findings highlight rules as a lever for accent control and a framework for evaluating disentanglement in speech generation.

Thanathai Lertpetchpun, Tiantian Feng, Dani Byrd et al.

Speech emotion recognition (SER) in naturalistic conditions presents a significant challenge for the speech processing community. Challenges include disagreement in labeling among annotators and imbalanced data distributions. This paper presents a reproducible framework that achieves superior (top 1) performance in the Emotion Recognition in Naturalistic Conditions Challenge (IS25-SER Challenge) - Task 2, evaluated on the MSP-Podcast dataset. Our system is designed to tackle the aforementioned challenges through multimodal learning, multi-task learning, and imbalanced data handling. Specifically, our best system is trained by adding text embeddings, predicting gender, and including ``Other'' (O) and ``No Agreement'' (X) samples in the training set. Our system's results secured both first and second places in the IS25-SER Challenge, and the top performance was achieved by a simple two-system ensemble.

Thanapat Trachu, Thanathai Lertpetchpun, Sai Praneeth Karimireddy et al.

Zero-shot Text-to-Speech (TTS) voice cloning poses severe privacy risks, demanding the removal of specific speaker identities from trained TTS models. Conventional machine unlearning is insufficient in this context, as zero-shot TTS can dynamically reconstruct voices from just reference prompts. We formalize this task as Speech Generation Speaker Poisoning (SGSP), in which we modify trained models to prevent the generation of specific identities while preserving utility for other speakers. We evaluate inference-time filtering and parameter-modification baselines across 1, 15, and 100 forgotten speakers. Performance is assessed through the trade-off between utility (WER) and privacy, quantified using AUC and Forget Speaker Similarity (FSSIM). We achieve strong privacy for up to 15 speakers but reveal scalability limits at 100 speakers due to increased identity overlap. Our study thus introduces a novel problem and evaluation framework toward further advances in generative voice privacy.

Thanathai Lertpetchpun, Yoonjeong Lee, Jihwan Lee et al.

Accent plays a crucial role in speaker identity and inclusivity in speech technologies. Existing accented text-to-speech (TTS) systems either require large-scale accented datasets or lack fine-grained phoneme-level controllability. We propose a accented TTS framework that combines phonological rules with a multilingual TTS model. The rules are applied to phoneme sequences to transform accent at the phoneme level while preserving intelligibility. The method requires no accented training data and enables explicit phoneme-level accent manipulation. We design rule sets for Spanish- and Indian-accented English, modeling systematic differences in consonants, vowels, and syllable structure arising from phonotactic constraints. We analyze the trade-off between phoneme-level duration alignment and accent as realized in speech timing. Experimental results demonstrate effective accent shift while maintaining speech quality.

Thanathai Lertpetchpun, Thanapat Trachu, Jihwan Lee et al.

Accent is an integral part of society, reflecting multiculturalism and shaping how individuals express identity. The majority of English speakers are non-native (L2) speakers, yet current Text-To-Speech (TTS) systems primarily model American-accented English due limited accented data. We propose \textit{Accent Vector}, a controllable representation that enables accent manipulation in multilingual TTS without requiring accented training data. \textit{Accent Vector} is derived by fine-tuning a TTS system on native speech of a different language (i.e. non-English) and computing task vectors capturing accent characteristics (i.e. in English). By scaling and interpolating the vector, we achieve fine-grained control over accent strength and generate mixed-accent speech. In addition, it generalizes beyond English, enabling accent control across multiple languages. Objective and human evaluations confirm the effectiveness of Accent Vector for fine-grained and compositional accent control.

Jihwan Lee, Sean Foley, Thanathai Lertpetchpun et al.

We propose ARTI-6, a compact six-dimensional articulatory speech encoding framework derived from real-time MRI data that captures crucial vocal tract regions including the velum, tongue root, and larynx. ARTI-6 consists of three components: (1) a six-dimensional articulatory feature set representing key regions of the vocal tract; (2) an articulatory inversion model, which predicts articulatory features from speech acoustics leveraging speech foundation models, achieving a prediction correlation of 0.87; and (3) an articulatory synthesis model, which reconstructs intelligible speech directly from articulatory features, showing that even a low-dimensional representation can generate natural-sounding speech. Together, ARTI-6 provides an interpretable, computationally efficient, and physiologically grounded framework for advancing articulatory inversion, synthesis, and broader speech technology applications. The source code and speech samples are publicly available.

Efthymios Tsaprazlis, Thanathai Lertpetchpun, Tiantian Feng et al.

Voice anonymization aims to conceal speaker identity and attributes while preserving intelligibility, but current evaluations rely almost exclusively on Equal Error Rate (EER) that obscures whether adversaries can mount high-precision attacks. We argue that privacy should instead be evaluated in the low false-positive rate (FPR) regime, where even a small number of successful identifications constitutes a meaningful breach. To this end, we introduce VoxGuard, a framework grounded in differential privacy and membership inference that formalizes two complementary notions: User Privacy, preventing speaker re-identification, and Attribute Privacy, protecting sensitive traits such as gender and accent. Across synthetic and real datasets, we find that informed adversaries, especially those using fine-tuned models and max-similarity scoring, achieve orders-of-magnitude stronger attacks at low-FPR despite similar EER. For attributes, we show that simple transparent attacks recover gender and accent with near-perfect accuracy even after anonymization. Our results demonstrate that EER substantially underestimates leakage, highlighting the need for low-FPR evaluation, and recommend VoxGuard as a benchmark for evaluating privacy leakage.