arXiv subjects

Abeer Alwan

Publications and source records attributed to Abeer Alwan.

At least 19 recordsLinked to original sources

arXiv2026

Hearing the Whispers: Black-Box Membership Inference Attacks on Finetuned TTS Models

Text-to-Speech (TTS) foundation models are increasingly fine-tuned on private datasets to synthesize highly personalized voices, introducing severe privacy risks by exposing both biometric identities and sensitive speech content. Existing black-box membership inference attacks (MIAs) follow a two-stage pipeline of query generation and representation engineering, both of which face unique challenges when adapted to TTS. For query generation, dual conditioning on synthesis text and reference speech creates a large and underexplored query design space with no established criterion for identifying an effective query. For representation engineering, the multi-level speech characteristics and temporal variability of speech make low-level representations and direct comparisons inadequate for capturing membership signals. To address these challenges, we present the first black-box MIA framework explicitly tailored to TTS models at both the speaker and record levels. For query generation, we characterize the feasible query space and establish two criteria, scorable extent and memorization elicitation, for evaluating five representative queries, identifying recitation as the strongest. For representation engineering, we obtain multi-level speech representations from embedding models and temporally align the generated and target audio for fine-grained comparison. Evaluations across three state-of-the-art TTS models (CosyVoice2, F5-TTS, and XTTS-v2) fine-tuned on two benchmark datasets (VCTK and British Dialect) reveal severe privacy leakage: speaker-level AUC remains above 0.80 and approaches 1.0 in the strongest settings, while record-level AUC ranges from 0.80 to 0.90 and remains effective even in challenging scenarios where both members and non-members are of the same speakers. We further identify speech characteristics associated with disproportionate vulnerability to memorization.

cs.CR↗

arXiv2026

Entropy-Aware Domain-Routed Mixture-of-Experts Speech-LLM Framework: A Case Study of Multi-Domain Child-Adult ASR

While Speech Large Language Models (Speech-LLMs) have achieved strong performance on adult Automatic Speech Recognition (ASR), their effectiveness on child speech remains under-explored, and single models often struggle to handle diverse adult and child age groups simultaneously. This paper proposes a Mixture-of-Experts (MoE) Speech-LLM for unified ASR across adult and child speech spanning diverse environments and age groups. The framework employs a Classifier-based Domain Router (C-DR) with a coarse-to-fine strategy and integrates both a Mixture-of-Projectors (MoP) and a Mixture-of-LoRAs (MoL) to model domain-specific variations. To address routing uncertainty near domain boundaries, an Entropy-Aware Routing (EAR) mechanism is introduced to dynamically incorporate a shared expert. Experiments on public child corpora demonstrate consistent improvements over baselines while preserving adult ASR performance. To our knowledge, this is the first work leveraging Speech-LLMs for unified, multi-domain ASR encompassing both children and adults.

eess.AS↗

arXiv2026

GC-LoRA: Gated Convolutional LoRA for Parameter-Efficient Acoustic Adaptation

Transformer-based Speech Foundation Models excel in most Automatic Speech Recognition tasks but often suffer performance degradation when applied to domains with mismatched acoustic characteristics. While Parameter Efficient Fine-Tuning (PEFT) methods, such as Low-Rank Adaptation (LoRA), adjust global attention, they lack the local context modeling crucial for capturing domain-specific variations. We propose GC-LoRA, a novel adapter architecture that injects Conformer-style local convolutional processing into pretrained Transformer encoders. By integrating a lightweight adapter to encoder attention output projections, our method efficiently captures local acoustic dependencies without disrupting pretrained global representations. Experiments across diverse datasets (acoustically-degraded, bandlimited, dialectal, child) demonstrate the efficacy of our approach, achieving Word Error Rate (WER) reductions of up to 10.9% compared to baselines while adding minimal trainable parameters.

eess.AS↗

arXiv2026

Gumbel-BEARD: Automatic Layer Selection for Self-Supervised Adaptation of Whisper in Low-Resource Domains

Speech foundation models often struggle in low-resource domains due to domain mismatch and data scarcity. We propose Gumbel-BEARD, a domain adaptation framework that automates Whisper encoder layer selection via an end-to-end trainable hard Gumbel-Softmax selector. It enables self-supervised adaptation with a BEST-RQ objective that dynamically adapts to target acoustic characteristics without manual tuning. Experiments on the MyST child speech corpus demonstrate efficiency and scalability: with 10 h of labeled data for fine-tuning, our method matches a fully supervised baseline trained on the complete 133 h labeled set. We establish new state-of-the-art word error rates (WERs) of 8.21% using Whisper-medium on MyST and 11.06% using Whisper-small on the OGI Spontaneous dataset. Evaluation on CORAAL further confirms robustness to adult dialectal domain shifts, with up to 6% relative WER reduction, highlighting the generalizability of our approach to diverse low-resource conditions.

eess.AS↗

arXiv2026

STACodec: Semantic Token Assignment for Balancing Acoustic Fidelity and Semantic Information in Audio Codecs

Neural audio codecs are widely used for audio compression and can be integrated into token-based language models. Traditional codecs preserve acoustic details well but lack semantic information. Recent hybrid codecs attempt to incorporate semantic information through distillation, but this often degrades reconstruction performance, making it difficult to achieve both. To address this limitation, we introduce STACodec, a unified codec that integrates semantic information from self-supervised learning (SSL) models into the first layer of residual vector quantization (RVQ-1) via semantic token assignment (STA). To further eliminate reliance on SSL-based semantic tokenizers and improve efficiency during inference, we propose a semantic pre-distillation (SPD) module, which predicts semantic tokens directly for assignment to the first RVQ layer during inference. Experimental results show that STACodec outperforms existing hybrid codecs in both audio reconstruction and downstream semantic tasks, demonstrating a better balance between acoustic fidelity and semantic capability.

eess.AS↗

arXiv2026

Mind the Shift: Using Delta SSL Embeddings to Enhance Child ASR

Self-supervised learning (SSL) models have achieved impressive results across many speech tasks, yet child automatic speech recognition (ASR) remains challenging due to limited data and pretraining domain mismatch. Fine-tuning SSL models on child speech induces shifts in the representation space. We hypothesize that delta SSL embeddings, defined as the differences between embeddings from a finetuned model and those from its pretrained counterpart, encode task-specific information that complements finetuned features from another SSL model. We evaluate multiple fusion strategies on the MyST childrens corpus using different models. Results show that delta embedding fusion with WavLM yields up to a 10 percent relative WER reduction for HuBERT and a 4.4 percent reduction for W2V2, compared to finetuned embedding fusion. Notably, fusing WavLM with delta W2V2 embeddings achieves a WER of 9.64, setting a new state of the art among SSL models on the MyST corpus. These findings demonstrate the effectiveness of delta embeddings and highlight feature fusion as a promising direction for advancing child ASR.

cs.CL↗

arXiv2025

Comparing Unsupervised and Supervised Semantic Speech Tokens: A Case Study of Child ASR

Discrete speech tokens have gained attention for their storage efficiency and integration with Large Language Models (LLMs). They are commonly categorized into acoustic and semantic tokens, with the latter being more advantageous for Automatic Speech Recognition (ASR). Traditionally, unsupervised K-means clustering has been used to extract semantic speech tokens from Speech Foundation Models (SFMs). Recently, supervised methods, such as finite scalar quantization (FSQ) trained with ASR loss, have emerged for speech generation. Both approaches leverage pre-trained SFMs, benefiting low-resource tasks such as child ASR. This paper systematically compares supervised and unsupervised semantic speech tokens for child ASR. Results show that supervised methods not only outperform unsupervised ones but even unexpectedly surpass continuous representations, and they perform well even in ultra-low bitrate settings. These findings highlight the advantages of supervised semantic tokens and offer insights for improving discrete speech tokenization.

eess.AS↗

arXiv2025

Benchmarking Training Paradigms, Dataset Composition, and Model Scaling for Child ASR in ESPnet

Despite advancements in ASR, child speech recognition remains challenging due to acoustic variability and limited annotated data. While fine-tuning adult ASR models on child speech is common, comparisons with flat-start training remain underexplored. We compare flat-start training across multiple datasets, SSL representations (WavLM, XEUS), and decoder architectures. Our results show that SSL representations are biased toward adult speech, with flat-start training on child speech mitigating these biases. We also analyze model scaling, finding consistent improvements up to 1B parameters, beyond which performance plateaus. Additionally, age-related ASR and speaker verification analysis highlights the limitations of proprietary models like Whisper, emphasizing the need for open-data models for reliable child speech research. All investigations are conducted using ESPnet, and our publicly available benchmark provides insights into training strategies for robust child speech processing.

cs.LG↗

arXiv2025

ProMode: A Speech Prosody Model Conditioned on Acoustic and Textual Inputs

Prosody conveys rich emotional and semantic information of the speech signal as well as individual idiosyncrasies. We propose a stand-alone model that maps text-to-prosodic features such as F0 and energy and can be used in downstream tasks such as TTS. The ProMode encoder takes as input acoustic features and time-aligned textual content, both are partially masked, and obtains a fixed-length latent prosodic embedding. The decoder predicts acoustics in the masked region using both the encoded prosody input and unmasked textual content. Trained on the GigaSpeech dataset, we compare our method with state-of-the-art style encoders. For F0 and energy predictions, we show consistent improvements for our model at different levels of granularity. We also integrate these predicted prosodic features into a TTS system and conduct perceptual tests, which show higher prosody preference compared to the baselines, demonstrating the model's potential in tasks where prosody modeling is important.

eess.AS↗

arXiv2025

G-IFT: A Gated Linear Unit adapter with Iterative Fine-Tuning for Low-Resource Children's Speaker Verification

Speaker Verification (SV) systems trained on adults speech often underperform on children's SV due to the acoustic mismatch, and limited children speech data makes fine-tuning not very effective. In this paper, we propose an innovative framework, a Gated Linear Unit adapter with Iterative Fine-Tuning (G-IFT), to enhance knowledge transfer efficiency between the high-resource adults speech domain and the low-resource children's speech domain. In this framework, a Gated Linear Unit adapter is first inserted between the pre-trained speaker embedding model and the classifier. Then the classifier, adapter, and pre-trained speaker embedding model are optimized sequentially in an iterative way. This framework is agnostic to the type of the underlying architecture of the SV system. Our experiments on ECAPA-TDNN, ResNet, and X-vector architectures using the OGI and MyST datasets demonstrate that the G-IFT framework yields consistent reductions in Equal Error Rates compared to baseline methods.

eess.AS↗

arXiv2025

An Age-Agnostic System for Robust Speaker Verification

In speaker verification (SV), the acoustic mismatch between children's and adults' speech leads to suboptimal performance when adult-trained SV systems are applied to children's speaker verification (C-SV). While domain adaptation techniques can enhance performance on C-SV tasks, they often do so at the expense of significant degradation in performance on adults' SV (A-SV) tasks. In this study, we propose an Age Agnostic Speaker Verification (AASV) system that achieves robust performance across both C-SV and A-SV tasks. Our approach employs a domain classifier to disentangle age-related attributes from speech and subsequently expands the embedding space using the extracted domain information, forming a unified speaker representation that is robust and highly discriminative across age groups. Experiments on the OGI and VoxCeleb datasets demonstrate the effectiveness of our approach in bridging SV performance disparities, laying the foundation for inclusive and age-adaptive SV systems.

eess.AS↗

arXiv2025

CHSER: A Dataset and Case Study on Generative Speech Error Correction for Child ASR

Automatic Speech Recognition (ASR) systems struggle with child speech due to its distinct acoustic and linguistic variability and limited availability of child speech datasets, leading to high transcription error rates. While ASR error correction (AEC) methods have improved adult speech transcription, their effectiveness on child speech remains largely unexplored. To address this, we introduce CHSER, a Generative Speech Error Correction (GenSEC) dataset for child speech, comprising 200K hypothesis-transcription pairs spanning diverse age groups and speaking styles. Results demonstrate that fine-tuning on the CHSER dataset achieves up to a 28.5% relative WER reduction in a zero-shot setting and a 13.3% reduction when applied to fine-tuned ASR systems. Additionally, our error analysis reveals that while GenSEC improves substitution and deletion errors, it struggles with insertions and child-specific disfluencies. These findings highlight the potential of GenSEC for improving child ASR.

eess.AS↗

arXiv2025

Enhancing Age-Related Robustness in Children Speaker Verification

One of the main challenges in children's speaker verification (C-SV) is the significant change in children's voices as they grow. In this paper, we propose two approaches to improve age-related robustness in C-SV. We first introduce a Feature Transform Adapter (FTA) module that integrates local patterns into higher-level global representations, reducing overfitting to specific local features and improving the inter-year SV performance of the system. We then employ Synthetic Audio Augmentation (SAA) to increase data diversity and size, thereby improving robustness against age-related changes. Since the lack of longitudinal speech datasets makes it difficult to measure age-related robustness of C-SV systems, we introduce a longitudinal dataset to assess inter-year verification robustness of C-SV systems. By integrating both of our proposed methods, the average equal error rate was reduced by 19.4%, 13.0%, and 6.1% in the one-year, two-year, and three-year gap inter-year evaluation sets, respectively, compared to the baseline.

eess.AS↗

arXiv2025

Selective Attention Merging for low resource tasks: A case study of Child ASR

While Speech Foundation Models (SFMs) excel in various speech tasks, their performance for low-resource tasks such as child Automatic Speech Recognition (ASR) is hampered by limited pretraining data. To address this, we explore different model merging techniques to leverage knowledge from models trained on larger, more diverse speech corpora. This paper also introduces Selective Attention (SA) Merge, a novel method that selectively merges task vectors from attention matrices to enhance SFM performance on low-resource tasks. Experiments on the MyST database show significant reductions in relative word error rate of up to 14%, outperforming existing model merging and data augmentation techniques. By combining data augmentation techniques with SA Merge, we achieve a new state-of-the-art WER of 8.69 on the MyST database for the Whisper-small model, highlighting the potential of SA Merge for improving low-resource ASR.

cs.CL↗

arXiv2024

Benchmarking Children's ASR with Supervised and Self-supervised Speech Foundation Models

Speech foundation models (SFMs) have achieved state-of-the-art results for various speech tasks in supervised (e.g. Whisper) or self-supervised systems (e.g. WavLM). However, the performance of SFMs for child ASR has not been systematically studied. In addition, there is no benchmark for child ASR with standard evaluations, making the comparisons of novel ideas difficult. In this paper, we initiate and present a comprehensive benchmark on several child speech databases based on various SFMs (Whisper, Wav2vec2.0, HuBERT, and WavLM). Moreover, we investigate finetuning strategies by comparing various data augmentation and parameter-efficient finetuning (PEFT) methods. We observe that the behaviors of these methods are different when the model size increases. For example, PEFT matches the performance of full finetuning for large models but worse for small models. To stabilize finetuning using augmented data, we propose a perturbation invariant finetuning (PIF) loss as a regularization.

eess.AS↗

arXiv2024

SOA: Reducing Domain Mismatch in SSL Pipeline by Speech Only Adaptation for Low Resource ASR

Recently, speech foundation models have gained popularity due to their superiority in finetuning downstream ASR tasks. However, models finetuned on certain domains, such as LibriSpeech (adult read speech), behave poorly on other domains (child or noisy speech). One solution could be collecting as much labeled and diverse data as possible for joint finetuning on various domains. However, collecting target domain speech-text paired data and retraining the model is often costly and computationally expensive. In this paper, we introduce a simple yet effective method, speech only adaptation (SOA), based on speech foundation models (Wav2vec 2.0), which requires only speech input data from the target domain. Specifically, the Wav2vec 2.0 feature encoder is continually pretrained with the Wav2vec 2.0 loss on both the source and target domain data for domain adaptation, while the contextual encoder is frozen. Compared to a source domain finetuned model with the feature encoder being frozen during training, we find that replacing the frozen feature encoder with the adapted one provides significant WER improvements to the target domain while preserving the performance of the source domain. The effectiveness of SOA is examined on various low resource or domain mismatched ASR settings, including adult-child and clean-noisy speech.

eess.AS↗

arXiv2024

UniEnc-CASSNAT: An Encoder-only Non-autoregressive ASR for Speech SSL Models

Non-autoregressive automatic speech recognition (NASR) models have gained attention due to their parallelism and fast inference. The encoder-based NASR, e.g. connectionist temporal classification (CTC), can be initialized from the speech foundation models (SFM) but does not account for any dependencies among intermediate tokens. The encoder-decoder-based NASR, like CTC alignment-based single-step non-autoregressive transformer (CASS-NAT), can mitigate the dependency problem but is not able to efficiently integrate SFM. Inspired by the success of recent work of speech-text joint pre-training with a shared transformer encoder, we propose a new encoder-based NASR, UniEnc-CASSNAT, to combine the advantages of CTC and CASS-NAT. UniEnc-CASSNAT consists of only an encoder as the major module, which can be the SFM. The encoder plays the role of both the CASS-NAT encoder and decoder by two forward passes. The first pass of the encoder accepts the speech signal as input, while the concatenation of the speech signal and the token-level acoustic embedding is used as the input for the second pass. Examined on the Librispeech 100h, MyST, and Aishell1 datasets, the proposed UniEnc-CASSNAT achieves state-of-the-art NASR results and is better or comparable to CASS-NAT with only an encoder and hence, fewer model parameters. Our codes are publicly available.

eess.AS↗

arXiv2023

Non-uniform Speaker Disentanglement For Depression Detection From Raw Speech Signals

While speech-based depression detection methods that use speaker-identity features, such as speaker embeddings, are popular, they often compromise patient privacy. To address this issue, we propose a speaker disentanglement method that utilizes a non-uniform mechanism of adversarial SID loss maximization. This is achieved by varying the adversarial weight between different layers of a model during training. We find that a greater adversarial weight for the initial layers leads to performance improvement. Our approach using the ECAPA-TDNN model achieves an F1-score of 0.7349 (a 3.7% improvement over audio-only SOTA) on the DAIC-WoZ dataset, while simultaneously reducing the speaker-identification accuracy by 50%. Our findings suggest that identifying depression through speech signals can be accomplished without placing undue reliance on a speaker's identity, paving the way for privacy-preserving approaches of depression detection.

eess.AS↗