arXiv subjects

Sung-Feng Huang

Publications and source records attributed to Sung-Feng Huang.

At least 19 recordsLinked to original sources

arXiv2026

HAMMER: Harmonic-Aware Parallel Context Modeling and Discriminator-Free Perceptual Optimization for Speech Enhancement

Recent speech enhancement systems combine self-attention and Mamba to capture global interactions and long-range dependencies. Yet these hybrids usually operate as sequence mixers and do not explicitly exploit harmonic periodicity, a strong cue for preserving voiced speech under noise. Perceptual optimization poses another challenge. PESQ is non-differentiable, so many methods train auxiliary metric discriminators that increase complexity and introduce adversarial instability. We propose \ours, a harmonic-aware and discriminator-free speech enhancer built around two components. (i) The Time-Frequency Harmonic-aware Attention-Mamba (TF-HAM) block runs self-attention and bidirectional Mamba in parallel along both spectrogram axes, then applies a speech-adapted autocorrelation feed-forward network to encode local periodic structure. (ii) Metric-explicit perceptual refinement (MEPR) combines differentiable PESQ and log-likelihood-ratio losses to expose perceptual metric structure without a learned surrogate. On VoiceBank+DEMAND, \ours achieves 3.69 PESQ and 4.41 COVL with only 2.39\,M parameters, outperforming or matching discriminator-based systems. Inference-time perceptual contrast stretching further raises PESQ to 3.79 without retraining. The source code will be available at https://github.com/shangfuu/HAMMER.git.

eess.AS↗

arXiv2026

RT-SEMamba: Real-Time Speech Enhancement Mamba via Progressive Knowledge Distillation

We present RT-SEMamba, a fully causal speech enhancement (SE) model built upon causal time-frequency Mamba blocks. Unlike Transformer-based architectures that rely on a growing key-value cache, Mamba propagates a fixed-size recurrent state per layer, enabling memory- and bandwidth-efficient long-form inference. We further introduce a progressive knowledge distillation (KD) strategy that compresses an 8-layer teacher into a shallow 1-layer student by jointly distilling complex spectral outputs and intermediate representations. On Voicebank-DEMAND, the 8-layer RT-SEMamba achieves 3.32 PESQ with a 25 ms algorithmic latency constraint, and the distilled 1-layer student improves over a naive 1-layer baseline from 3.06 to 3.18 PESQ while preserving the same steady-state RTF, delivering a 2.64x speedup over the teacher. These results demonstrate that state-space models with progressive KD provide a competitive quality-latency trade-off for real-time SE.

cs.SD↗

arXiv2026

VIBE: Voice-Induced open-ended Bias Evaluation for Large Audio-Language Models via Real-World Speech

Large Audio-Language Models (LALMs) are increasingly integrated into daily applications, yet their generative biases remain underexplored. Existing speech fairness benchmarks rely on synthetic speech and Multiple-Choice Questions (MCQs), both offering a fragmented view of fairness. We propose VIBE, a framework that evaluates generative bias through open-ended tasks such as personalized recommendations, using human-recorded speech. Unlike MCQs, our method allows stereotypical associations to manifest organically without predefined options, making it easily extensible to new tasks. Evaluating 12 state-of-the-art LALMs reveals systematic biases in realistic scenarios. Both gender and accent cues trigger statistically significant distributional shifts, and bias magnitude is strongly task-dependent.

eess.AS↗

arXiv2026

One Model, Many Latencies: Universal Speech Enhancement for Diverse Real-Time Applications

Different real-time speech applications impose distinct latency budgets, often requiring separately trained enhancement models for each scenario. In this paper, we propose a one-for-all, real-time universal speech enhancement model that provides explicit control over both algorithmic and computational latency. Algorithmic latency is flexibly adjusted via configurable look-ahead frames. To avoid learning inefficiency caused by varying padding configurations, we introduce parallel convolutional layers corresponding to different look-ahead settings. Computational latency is controlled through an early-exit mechanism, enabling inference at different network depths. To narrow the performance gap between specialized and flexible models, we propose a two-stage training strategy with a shared-to-multiple decoder transition. Overall, the proposed framework enables a single model to be deployed across diverse latency budgets without retraining separate models. Model weights are available for download at: https://huggingface.co/nvidia/Real-time_RE-USE

cs.SD↗

arXiv2026

Rethinking Training Targets, Architectures and Data Quality for Universal Speech Enhancement

Universal Speech Enhancement (USE) aims to restore speech quality under diverse degradation conditions while preserving signal fidelity. Despite recent progress, key challenges in training target selection, the distortion--perception tradeoff, and data curation remain unresolved. In this work, we systematically address these three overlooked problems. First, we revisit the conventional practice of using early-reflected speech as the dereverberation target and show that it can degrade perceptual quality and downstream ASR performance. We instead demonstrate that time-shifted anechoic clean speech provides a superior learning target. Second, guided by the distortion--perception tradeoff theory, we propose a simple two-stage framework that achieves minimal distortion under a given level of perceptual quality. Third, we analyze the trade-off between training data scale and quality for USE, revealing that training on large uncurated corpora imposes a performance ceiling, as models struggle to remove subtle artifacts. Our method achieves state-of-the-art performance on the URGENT 2025 non-blind test set and exhibits strong language-agnostic generalization, making it effective for improving TTS training data. Model weights are available for download at: https://huggingface.co/nvidia/RE-USE.

cs.SD↗

arXiv2026

MoVE: Translating Laughter and Tears via Mixture of Vocalization Experts in Speech-to-Speech Translation

Recent Speech-to-Speech Translation (S2ST) systems achieve strong semantic accuracy yet consistently strip away non-verbal vocalizations (NVs), such as laughter and crying that convey pragmatic intent, which severely limits real-world utility. We address this via three contributions. First, we propose a synthesis pipeline for building scalable expressive datasets to overcome the data scarcity limitation. Second, we propose MoVE, a Mixture-of-LoRA-Experts architecture with expressive-specialized adapters and a soft-weighting router that blends experts for capturing hybrid expressive states. Third, we show pretrained AudioLLMs enable striking data efficiency: 30 minutes of curated data is enough for strong performance. On English-Chinese S2ST, while comparing with strong baselines, MoVE reproduces target NVs in 76% of cases and achieves the highest human-rated naturalness and emotional fidelity among all compared systems, where existing S2ST systems preserve at most 14% of NVs.

cs.CL↗

arXiv2026

Joint Fullband-Subband Modeling for High-Resolution SingFake Detection

Rapid advances in singing voice synthesis have increased unauthorized imitation risks, creating an urgent need for better Singing Voice Deepfake (SingFake) Detection, also known as SVDD. Unlike speech, singing contains complex pitch, wide dynamic range, and timbral variations. Conventional 16 kHz-sampled detectors prove inadequate, as they discard vital high-frequency information. This study presents the first systematic analysis of high-resolution (44.1 kHz sampling rate) audio for SVDD. We propose a joint fullband-subband modeling framework: the fullband captures global context, while subband-specific experts isolate fine-grained synthesis artifacts unevenly distributed across the spectrum. Experiments on the WildSVDD dataset demonstrate that high-frequency subbands provide essential complementary cues. Our framework significantly outperforms 16 kHz-sampled models, proving that high-resolution audio and strategic subband integration are critical for robust in-the-wild detection.

cs.SD↗

arXiv2026

DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment

We introduce DeSTA2.5-Audio, a general-purpose Large Audio Language Model (LALM) designed for robust auditory perception and instruction-following. Recent LALMs augment Large Language Models (LLMs) with auditory capabilities by training on large-scale audio-instruction datasets. However, existing LALMs have often suffered from the catastrophic forgetting of the LLM's original abilities. Therefore, balancing knowledge retention and audio perception has become a critical challenge. To address this, we revisit the data construction pipeline and propose a self-generated cross-modal alignment strategy in which the backbone LLM generates its own training targets, named DeSTA. This approach aims at preserving the LLM's native language proficiency thereby enabling zero-shot generalization without task-specific tuning. We construct DeSTA-AQA5M, a large-scale, task-agnostic dataset containing 5 million training samples derived from 7,000 hours of audio spanning 50 diverse datasets, including speech, environmental sounds, and music. DeSTA2.5-Audio achieves state-of-the-art or competitive performance across a wide range of audio-language benchmarks, including Dynamic-SUPERB, MMAU, SAKURA, Speech-IFEval, and VoiceBench. Comprehensive comparative studies demonstrate that our self-generated strategy outperforms existing training strategies. Our findings underscore the importance of carefully designed data construction in LALM development and offer practical insights for building robust, general-purpose LALMs.

eess.AS↗

arXiv2026

How Auditory Knowledge in LLM Backbones Shapes Audio Language Models: A Holistic Evaluation

Large language models (LLMs) have been widely used as knowledge backbones of Large Audio Language Models (LALMs), yet how much auditory knowledge they encode through text-only pre-training and how this affects downstream performance remains unclear. We study this gap by comparing different LLMs under two text-only and one audio-grounded setting: (1) direct probing on AKB-2000, a curated benchmark testing the breadth and depth of auditory knowledge; (2) cascade evaluation, where LLMs reason over text descriptions from an audio captioner; and (3) audio-grounded evaluation, where each LLM is fine-tuned into a Large Audio Language Model (LALM) with an audio encoder. Our findings reveal that auditory knowledge varies substantially across families, and text-only results are strongly correlated with audio performance. Our work provides empirical grounding for a comprehensive understanding of LLMs in audio research.

eess.AS↗

arXiv2026

SAKE: Towards Editing Auditory Attribute Knowledge of Large Audio-Language Models

Knowledge editing enables targeted updates without retraining, but prior work focuses on textual or visual facts, leaving abstract auditory perceptual knowledge underexplored. We introduce SAKE, the first benchmark for editing perceptual auditory attribute knowledge in large audio-language models (LALMs), which requires modifying acoustic generalization rather than isolated facts. We evaluate eight diverse editing methods on three LALMs across reliability, generality, locality, and portability, under single and sequential edits. Results show that most methods enforce edits reliably but struggle with auditory generalization, intra-attribute locality, and multimodal knowledge propagation, and often exhibit forgetting or degeneration in sequential editing. Additionally, fine-tuning the modality connector emerges as a more robust and balanced baseline compared with directly editing the LLM backbones. SAKE reveals key limitations of current methods and provides a foundation for developing auditory-specific LALM editing techniques.

cs.SD↗

arXiv2026

How Does Instrumental Music Help SingFake Detection?

Although many models exist to detect singing voice deepfakes (SingFake), how these models operate, particularly with instrumental accompaniment, is unclear. We investigate how instrumental music affects SingFake detection from two perspectives. To investigate the behavioral effect, we test different backbones, unpaired instrumental tracks, and frequency subbands. To analyze the representational effect, we probe how fine-tuning alters encoders' speech and music capabilities. Our results show that instrumental accompaniment acts mainly as data augmentation rather than providing intrinsic cues (e.g., rhythm or harmony). Furthermore, fine-tuning increases reliance on shallow speaker features while reducing sensitivity to content, paralinguistic, and semantic information. These insights clarify how models exploit vocal versus instrumental cues and can inform the design of more interpretable and robust SingFake detection systems.

cs.SD↗

arXiv2025

Investigating Safety Vulnerabilities of Large Audio-Language Models Under Speaker Emotional Variations

Large audio-language models (LALMs) extend text-based LLMs with auditory understanding, offering new opportunities for multimodal applications. While their perception, reasoning, and task performance have been widely studied, their safety alignment under paralinguistic variation remains underexplored. This work systematically investigates the role of speaker emotion. We construct a dataset of malicious speech instructions expressed across multiple emotions and intensities, and evaluate several state-of-the-art LALMs. Our results reveal substantial safety inconsistencies: different emotions elicit varying levels of unsafe responses, and the effect of intensity is non-monotonic, with medium expressions often posing the greatest risk. These findings highlight an overlooked vulnerability in LALMs and call for alignment strategies explicitly designed to ensure robustness under emotional variation, a prerequisite for trustworthy deployment in real-world settings.

cs.SD↗

arXiv2025

Leveraging Mamba with Full-Face Vision for Audio-Visual Speech Enhancement

Recent Mamba-based models have shown promise in speech enhancement by efficiently modeling long-range temporal dependencies. However, models like Speech Enhancement Mamba (SEMamba) remain limited to single-speaker scenarios and struggle in complex multi-speaker environments such as the cocktail party problem. To overcome this, we introduce AVSEMamba, an audio-visual speech enhancement model that integrates full-face visual cues with a Mamba-based temporal backbone. By leveraging spatiotemporal visual information, AVSEMamba enables more accurate extraction of target speech in challenging conditions. Evaluated on the AVSEC-4 Challenge development and blind test sets, AVSEMamba outperforms other monaural baselines in speech intelligibility (STOI), perceptual quality (PESQ), and non-intrusive quality (UTMOS), and achieves \textbf{1st place} on the monaural leaderboard.

cs.SD↗

arXiv2025

HighRateMOS: Sampling-Rate Aware Modeling for Speech Quality Assessment

Modern speech quality prediction models are trained on audio data resampled to a specific sampling rate. When faced with higher-rate audio at test time, these models can produce biased scores. We introduce HighRateMOS, the first non-intrusive mean opinion score (MOS) model that explicitly considers sampling rate. HighRateMOS ensembles three model variants that exploit the following information: (i) a learnable embedding of speech sampling rate, (ii) Wav2vec 2.0 self-supervised embeddings, (iii) multi-scale CNN spectral features, and (iv) MFCC features. In AudioMOS 2025 Track3, HighRateMOS ranked first in five out of eight metrics. Our experiments confirm that modeling the sampling rate directly leads to more robust and sampling-rate-agnostic speech quality predictions.

eess.AS↗

arXiv2025

Detecting the Undetectable: Assessing the Efficacy of Current Spoof Detection Methods Against Seamless Speech Edits

Neural speech editing advancements have raised concerns about their misuse in spoofing attacks. Traditional partially edited speech corpora primarily focus on cut-and-paste edits, which, while maintaining speaker consistency, often introduce detectable discontinuities. Recent methods, like A\textsuperscript{3}T and Voicebox, improve transitions by leveraging contextual information. To foster spoofing detection research, we introduce the Speech INfilling Edit (SINE) dataset, created with Voicebox. We detailed the process of re-implementing Voicebox training and dataset creation. Subjective evaluations confirm that speech edited using this novel technique is more challenging to detect than conventional cut-and-paste methods. Despite human difficulty, experimental results demonstrate that self-supervised-based detectors can achieve remarkable performance in detection, localization, and generalization across different edit methods. The dataset and related models will be made publicly available.

cs.SD↗

arXiv2024

Generative Speech Foundation Model Pretraining for High-Quality Speech Extraction and Restoration

This paper proposes a generative pretraining foundation model for high-quality speech restoration tasks. By directly operating on complex-valued short-time Fourier transform coefficients, our model does not rely on any vocoders for time-domain signal reconstruction. As a result, our model simplifies the synthesis process and removes the quality upper-bound introduced by any mel-spectrogram vocoder compared to prior work SpeechFlow. The proposed method is evaluated on multiple speech restoration tasks, including speech denoising, bandwidth extension, codec artifact removal, and target speaker extraction. In all scenarios, finetuning our pretrained model results in superior performance over strong baselines. Notably, in the target speaker extraction task, our model outperforms existing systems, including those leveraging SSL-pretrained encoders like WavLM. The code and the pretrained checkpoints are publicly available in the NVIDIA NeMo framework.

eess.AS↗

arXiv2024

Maximizing Data Efficiency for Cross-Lingual TTS Adaptation by Self-Supervised Representation Mixing and Embedding Initialization

This paper presents an effective transfer learning framework for language adaptation in text-to-speech systems, with a focus on achieving language adaptation using minimal labeled and unlabeled data. While many works focus on reducing the usage of labeled data, very few consider minimizing the usage of unlabeled data. By utilizing self-supervised features in the pretraining stage, replacing the noisy portion of pseudo labels with these features during fine-tuning, and incorporating an embedding initialization trick, our method leverages more information from unlabeled data compared to conventional approaches. Experimental results show that our framework is able to synthesize intelligible speech in unseen languages with only 4 utterances of labeled data and 15 minutes of unlabeled data. Our methodology continues to surpass conventional techniques, even when a greater volume of data is accessible. These findings highlight the potential of our data-efficient language adaptation framework.

cs.CL↗

arXiv2023

Personalized Lightweight Text-to-Speech: Voice Cloning with Adaptive Structured Pruning

Personalized TTS is an exciting and highly desired application that allows users to train their TTS voice using only a few recordings. However, TTS training typically requires many hours of recording and a large model, making it unsuitable for deployment on mobile devices. To overcome this limitation, related works typically require fine-tuning a pre-trained TTS model to preserve its ability to generate high-quality audio samples while adapting to the target speaker's voice. This process is commonly referred to as ``voice cloning.'' Although related works have achieved significant success in changing the TTS model's voice, they are still required to fine-tune from a large pre-trained model, resulting in a significant size for the voice-cloned model. In this paper, we propose applying trainable structured pruning to voice cloning. By training the structured pruning masks with voice-cloning data, we can produce a unique pruned model for each target speaker. Our experiments demonstrate that using learnable structured pruning, we can compress the model size to 7 times smaller while achieving comparable voice-cloning performance.

cs.SD↗