arXiv subjects

Zhen-Hua Ling

Publications and source records attributed to Zhen-Hua Ling.

At least 19 recordsLinked to original sources

arXiv2026

AKDQ: Adaptive Key-Delta Quantization for Low-Bitrate RVQ-based Neural Speech Codecs

Low-bitrate speech coding is essential for bandwidth-constrained channels and on-device applications, but conventional residual vector quantization (RVQ)-based codecs employ a fixed number of codebooks per frame regardless of content. Adjacent speech frames often exhibit strong similarity, and quantizing them independently with the same scheme results in redundant encoding, thereby wasting bitrate. Therefore, we propose Adaptive Key-Delta Quantization (AKDQ), which replaces the fixed per-frame VQ allocation of RVQ with an adaptive frame-wise key-or-delta policy. AKDQ is a plug-in strategy that requires no modification to the codec's encoder-decoder backbone. Specifically, in AKDQ, each frame is classified as either a key-frame (K-frame) quantized with all VQs, or a delta-frame (D-frame) quantized with only a few VQs on a delta correction from the previous reconstruction, thereby reducing bitrate. The K/D decision is made by a budget-aware causal scheduler through a bit-bank mechanism, keeping the system streamable with no additional lookahead. Experiments on both causal and non-causal codec families demonstrate that AKDQ effectively reduces bitrate redundancy. For instance, on DAC, using AKDQ at 1.5 kbps achieves reconstruction quality comparable to using the baseline RVQ at 2.0 kbps, saving 25% of the bitrate.

eess.AS↗

arXiv2026

ADReasoner: Acoustic-Linguistic Cue-Aware Reinforcement Learning for Explainable Alzheimer's Disease Detection from Speech

Speech-based Alzheimer's Disease (AD) detection holds significant promise due to its scalable and non-invasive nature. However, current Speech Large Language Models (SpeechLLMs), similar to conventional AD detection systems, still treat AD detection primarily as a simple categorical classification task. This paradigm provides limited interpretability of predictions, while leaving the inherent expressiveness and reasoning capabilities of SpeechLLMs largely underutilized. In this work, we take the first step toward reframing AD detection as a deep reasoning task via Reinforcement Learning (RL). We propose ADReasoner, an RL-enhanced SpeechLLM designed to generate accurate diagnostic predictions with interpretable rationales grounded in fine-grained acoustic-linguistic cues. To achieve this, we first systematically construct ADCoT-7K, an AD speech reasoning dataset combining real data and our quality-filtered synthetic data, where each instance features Chain-of-Thought (CoT) annotations and detailed captions. Second, observing the weak perception of AD-related acoustic-linguistic cues in current SpeechLLMs, we leverage Supervised Fine-Tuning (SFT) to develop a cue-perception-enhanced foundation model, ADReasoner-Base, thereby improving AD speech understanding. Third, alongside two standard rule-based rewards, we introduce a reasoning reward and a reasoning-label consistency reward into Group Relative Policy Optimization (GRPO) for RL. Furthermore, a shrinkage mechanism is employed to suppress misleading reasoning signals, while a gating mechanism progressively introduces both rewards to stabilize policy training. Experiments on three AD datasets (Pitt, PROCESS-1, PROCESS-2) demonstrate that ADReasoner outperforms previous state-of-the-art models in both detection performance and explanation quality, advancing AD detection toward interpretable reasoning from speech.

eess.AS↗

arXiv2026

Dual Task Vector Merging: Leveraging Emotion and ASR Knowledge for Low-Resource Alzheimer's Disease Detection

Alzheimer's Disease (AD) detection from speech benefits from both paralinguistic and linguistic cues, yet model training is frequently constrained by limited data. Fine-tuning a large pretrained speech encoder can easily overfit, while a frozen probe leaves the encoder's task-relevant knowledge underutilized. Therefore, we propose Dual Task Vector Merging, a parameter-efficient method that adapts a frozen wav2vec 2.0 backbone using task knowledge learned outside the AD task. Specifically, we inject two task vectors, derived as weight deltas from emotion- and ASR-fine-tuned wav2vec 2.0 models, into each transformer layer. During AD training, only layer-wise merging coefficients and a linear classification head are optimized, updating less than 0.1% of the parameters required for full fine-tuning. Speaker-independent experiments on ADReSS and ADReSSo show that dual merging improves over frozen probes, LoRA, and full fine-tuning, in the main binary settings, and gives the best results when combined with LoRA. Evaluation on PROCESS further shows that our advantages transfer to three-class HC/MCI/dementia classification when paired with LoRA. Experiments under reduced training data (20%, 40%, and 80%) confirm reliable gains in low-resource settings.

eess.AS↗

arXiv2026

ConsensusBench: Benchmark of Consensus Nodes for LLM Reasoning via Outcome Reward Densifying

Reinforcement learning (RL) has become one of the primary paradigms for reasoning enhancement of large language models (LLMs). In particular, Group Relative Policy Optimization (GRPO) and related algorithms have demonstrated strong performance with outcome-level rewards. However, these methods depend solely on the final answer, without feedback regarding which intermediate steps contribute to success or failure. As task complexity and reasoning trajectory length increase, such sparse final-answer rewards become increasingly insufficient. To address this limitation, we introduce ConsensusBench, a novel dataset designed to provide rule-based process-level signals. We posit that a correct final answer relies on a small set of intermediate conclusions throughout the reasoning process, which can be seen as a verifiable sub-outcome. We identify these sub-outcomes by filtering correct trajectories from N rollouts and clustering semantically equivalent intermediate statements. We call these clustered statements as Consensus Nodes. By integrating a rule-based process reward derived from these nodes into GRPO-style algorithms, we develop a new reinforcement learning signal named ConsensusPR. It directly reduces the reward sparsity of outcome reward across long reasoning trajectories. To facilitate systematic process-level evaluation, we introduce three metrics to our benchmark: Final Answer Accuracy (Acc), Node Coverage Rate (NCR), and Tokens per Node (TPN). Experiments across AIME 2024, AIME 2025, GSM8K, MATH-500, and our ConsensusBench demonstrate that the proposed method consistently surpasses GRPO-style approaches, highlighting the practical value of consensus nodes in guiding reasoning.

cs.CL↗

arXiv2026

Enhancing Neural Speech Coding with Semantic and Visual Cues

At low bitrates, neural speech codecs have limited capacity to encode all information needed for high-quality re construction, especially when relying solely on speech-derived representations. To address this limitation, this paper proposes a Semantic- and Visual-enhanced Speech Codec (SVSC), which in corporates semantic and visual cues into the neural speech coding process. Specifically, built upon a mainstream neural speech cod ing architecture, SVSC introduces a semantic encoding-decoding branch and an image analysis-synthesis branch. It fuses deep semantic features with visual cues through a cross-attention mech anism, forming an auxiliary high-level representation enriched with contextual and articulatory information. To handle different inference scenarios, SVSC introduces two information-injection strategies based on the availability of auxiliary semantic and vi sual cues. When such cues are available, the fusion mode directly incorporates the auxiliary representations into the speech coding branch through feature concatenation; otherwise, the distillation mode transfers auxiliary information into the speech coding branch through knowledge distillation during training, enabling speech-only inference without additional inputs. Experimental results validate the effectiveness of incorporating semantic and visual cues, improving the ViSQOL score of reconstructed speech from 3.86 to 4.01.

eess.AS↗

arXiv2026

Neural Music Enhancement with Dual Time-Frequency Spectral Representations for Prediction and Discrimination

Non-professional music recordings shared online often suffer from background noise and reverberation, degrading perceived quality and limiting reuse. This paper proposes DSME, a music enhancement model based on dual time-frequency spectral representations. Within a generative adversarial framework, DSME uses short-time Fourier transform (STFT) spectra for generation and constant-Q transform (CQT) spectra for discrimination. Leveraging STFT's fixed window, invertibility, and predictability, the generator estimates clean amplitude-phase spectra from degraded inputs and reconstructs waveforms via inverse STFT. Exploiting CQT's log-frequency, variable-window structure aligned with musical octaves, we design an octave-segmented CQT discriminator. We also introduce a chroma-spectrum loss to emphasize pitch and harmonic consistency. Experiments show DSME outperforms baselines in objective and subjective tests, validating the effectiveness of the dual-spectrum approach.

cs.SD↗

arXiv2026

PACodec: A Low-bitrate Neural Speech Codec with Parallel Additive Vector Quantization

This paper proposes PACodec, a novel low-bitrate neural speech codec based on parallel additive vector quantization (PAVQ). Unlike the mainstream residual vector quantization (RVQ) used in most neural speech codecs, where vector quantizers (VQs) are sequentially dependent, the PAVQ strategy adopted in PACodec aggregates parallel quantization results to optimize bitrate usage. Specifically, the PAVQ adopts a "global-local-global" (GLG) design: the global encoded features are quantized in parallel by multiple independent VQs, each attending to a local component of the representation, and their outputs are aggregated through addition to yield the final global quantization result for decoding. Experimental results show that PACodec, as each VQ focuses only on local information, supports smaller codebooks and reduces bitrate by 30% compared with baselines at the same decoding quality, with only minor model complexity. Further analysis shows that, owing to the GLG framework of PAVQ, the proposed PACodec is disentanglement-friendly, and each independent VQ captures different aspects of speech, e.g., content, timbre, and acoustic details, suggesting potential for application to downstream tasks such as voice conversion.

cs.SD↗

arXiv2026

StreamWSR: Streamable and Lightweight Waveform-Domain Neural Speech Super-Resolution

This paper proposes StreamWSR, a Streamable neural Waveform-domain model for speech Super-Resolution (SR). By adopting a fully causal architecture with compact frame-level waveform representation, the proposed StreamWSR supports zero-look-ahead streaming inference while avoiding vocoder-based reconstruction and explicit phase prediction. Specifically, StreamWSR downsamples the input waveform into a compact frame-level representation using strided causal convolutions. Then, a lightweight causal long-short-term modeling backbone is employed to capture both local waveform structures and long-range historical dependencies under causal constraints. Finally, the modeled output is converted back to the waveform domain through a causal transposed-convolution and combined with the input waveform via a residual connection to generate the final high-resolution speech. Experimental results on 16 kHz speech SR show that StreamWSR achieves competitive or superior speech quality and intelligibility compared with representative waveform- and spectrum-based baselines, while maintaining a zero-look-ahead streaming advantage with only 9M parameters and 2G FLOPs.

eess.AS↗

arXiv2026

Deep Neural Compression for RIR-Characterized Acoustic Environments with Structure-Aware Constraints

Room impulse responses (RIRs) characterize the acoustic environment of a room by capturing how sound propagates and decays within an enclosed space. In applications such as immersive audio rendering, accurate acoustic reconstruction often relies on spatially densely sampled RIRs. This consequently gives rise to a large volume of RIR data, imposing a substantial burden on storage. Although recent neural audio codecs provide an effective framework for low-bitrate compression, their training objectives are mainly tailored to speech and general audio, and are therefore not well aligned with the acoustic characteristics of RIRs. Therefore, we propose an EnCodec-based neural RIR compression method, which incorporates RIR structure-aware constraints at two levels. Specifically, at the RIR level, structure-aware constraints are imposed on the global decay behavior and local energy distribution of RIRs through energy decay curve (EDC) regularization and a short-time window energy constraint, while at the reverberant-speech level, reverberant-speech supervision is further introduced to constrain the consistency of the reverberant speech generated by the reconstructed RIRs. Experimental results show that, at a low bitrate of 375 bps, the proposed method achieves lower RIR reconstruction error and better reverberant-speech perceptual consistency than audio-oriented codecs.

eess.AS↗

arXiv2026

REINS: Refusal-Enhanced Inhibitory Steering with Sparse Autoencoder Features

Steering with Sparse Autoencoders (SAEs) offers a lightweight inference-time path for adapting the behavior of large language models without retraining. By exposing sparse and interpretable features, SAE steering provides a promising interface for safety control that guides harmful continuations toward refusal. However, we observe that complex wrappers can still undermine existing SAE steering methods on harmful prompts. To evaluate this failure mode systematically, we construct Generalized Undercover Instruction Safety Evaluation (GUISE), a dataset of harmful prompts with complex wrappers. Existing single direction SAE steering methods do not reliably produce refusals on harmful prompts, suggesting that refusal enhancement alone can be too weak when the harmful continuation path remains active. This motivates us to propose Refusal-Enhanced INhibitory Steering (REINS), which suppresses harmful continuation features and enhances safe refusal features in the same SAE feature space. Experiments on GUISE and other datasets show that prior methods either intervene too weakly or achieve only apparent safety through collapse, while REINS substantially reduces harmful responses, markedly improves safe refusals and largely preserves general capabilities.

cs.AI↗

arXiv2026

Short Horizons and Sparse Concepts: a Mathematical View of the Readout in the J-lens

The Jacobian lens (J-lens) has been proposed as a way to read verbalizable representations from language models. However, its principle and meaning lack a detailed and theoretical discussion. We provide a mathematical view of this interpretation and of its assumed causal structure. Besides treating the J-lens as a heuristic probe, we further regard it as a first-order causal transfer operator from intermediate activations to expected future readouts. We study the Jacobian matrix as the optimal local linear approximation of the downstream mapping, analyze its global approximation behavior and bias, and identify its mathematical meaning as an expectation over anticipated future readouts. Further analysis of the Jacobian energy distribution reveals that its causal geometry is highly sparse. The energy decays with depth, concentrates in an extremely small proportion, and decomposes into diagonal pathways and specific critical positions. This decomposition further resolves the expectation of the J-lens over future outputs into short-horizon and sparse concept predictions, providing a more intuitive attribution and explanation for the ability of the J-lens to visualize concepts during the thinking process. Based on the theory, we propose a simple but effective improvement strategy and decoupling method for the J-lens, which significantly enhances the ability of the J-lens to read out correct intermediate concepts.

cs.CL↗

arXiv2026

Towards Real-world Environment-aware Zero-shot Text-to-speech Synthesis via Disentangled Audio Infilling

Recent zero-shot text-to-speech (TTS) systems achieve remarkable naturalness and speaker similarity but typically require high-quality speaker prompts and either strip away or entangle the acoustic environment with speaker characteristics, limiting their real-world applicability. We present an extended DAIEN-TTS, an environment-aware zero-shot TTS framework that disentangles and jointly models speech, background noise, and reverberation, enabling independent control over timbre and acoustic environment through separate speaker and environment prompts. Built upon the flow-matching-based F5-TTS, it uses a speech-environment separation module to decompose environmental speech into speech, noise, and reverberation components, which are injected into the Diffusion Transformer for environment-aware generation. Training uses simulated data constructed by mixing clean speech with noise and room impulse responses, together with a cross-speaker conditioning strategy that suppresses speaker information leakage from the environment branch. When real-world data are available, the system can be further fine-tuned to bridge the simulated-to-real domain gap.At inference, a triple classifier-free guidance mechanism enables fine-grained control over speech, noise, and reverberation, and a signal-to-noise-ratio adaptation strategy aligns the synthesized speech with the environment prompt. Experiments on simulated and real-world test sets show that DAIEN-TTS generates environmental personalized speech with high naturalness, strong speaker similarity, and faithful noise and reverberation reproduction, while offering controllability beyond prior environment-aware TTS systems.

eess.AS↗

arXiv2026

LatentFlowSR: High-Fidelity Audio Super-Resolution via Noise-Robust Latent Flow Matching

Audio super-resolution aims to recover missing high-frequency details from bandwidth-limited low-resolution audio, thereby improving the naturalness and perceptual quality of the reconstructed signal. However, most existing methods directly operate in the waveform or time-frequency domain, which not only involves high-dimensional generation spaces but is also largely limited to speech tasks, leaving substantial room for improvement on more complex audio types such as sound effects and music. To mitigate these limitations, we introduce LatentFlowSR, a new audio super-resolution approach that leverages conditional flow matching (CFM) within a latent representation space. Specifically, we first train a noise-robust autoencoder, which encodes low-resolution audio into a continuous latent space. Conditioned on the low-resolution latent representation, a CFM mechanism progressively generates the corresponding high-resolution latent representation from a Gaussian prior with a one-step ordinary differential equation (ODE) solver. The resulting high-resolution latent representation is then decoded by the pretrained autoencoder to reconstruct the high-resolution audio. Experimental results demonstrate that LatentFlowSR achieves competitive or superior performance compared with baseline methods across various audio types and super-resolution settings. These results indicate that the proposed method possesses strong high-frequency reconstruction capability and robust generalization performance, providing compelling evidence for the effectiveness of latent-space modeling in audio super-resolution. All relevant code will be made publicly available upon completion of the paper review process.

cs.SD↗

arXiv2026

CoSTA: Cognitive-State-Conditioned TTS Data Augmentation Using ASR Transcripts for Alzheimer's Disease Detection

Speech-based Alzheimer's Disease (AD) detection is constrained by scarce pathological speech data. To address this, we propose CoSTA, a Text-to-Speech (TTS)-based data augmentation framework. Specifically, we first develop two Cognitive-State-Conditioned (CS-Cond) TTS models by adapting CosyVoice2 and F5-TTS to synthesize speech with distinct AD and Healthy Control characteristics. Furthermore, by constructing a transcript pool comprising Manual Transcripts (MT) and 36 Automatic Speech Recognition (ASR) transcripts, we investigate the impact of text sources on TTS-based augmentation. We also perform augmentation-factor analysis and test-time augmentation. Experiments on the ADReSS dataset show that CS-Cond TTS significantly improves synthetic speech utility, and ASR-driven augmentation frequently outperforms MT-driven augmentation. Finally, CoSTA yields a 4.16% gain over the baseline, achieving an audio-only accuracy of 85.83% on the ADReSS test set and outperforming prior methods.

eess.AS↗

arXiv2026

DuraMark: Duration-Embedded Watermarking in LLM-based TTS

Large language model (LLM)-based text-to-speech (TTS) models have achieved remarkable voice cloning capabilities, raising concerns about potential deepfake misuse. Speech watermarking mitigates this by embedding traceable information into generated speech. Mainstream watermarking methods operate at the signal level (waveform or spectrogram), rendering the watermark vulnerable to generative attacks (e.g., neural codec and vocoder). To address this, we propose DuraMark, a robust information-level watermarking framework. It utilizes syllable duration editing to achieve watermark embedding. Specifically, DuraMark integrates a duration-controllable LLM-based TTS model to edit syllable durations during synthesis, coupled with a duration extractor to extract these durations for detection. Experiments demonstrate DuraMark's superior robustness against generative attacks, significantly outperforming signal-level baselines. Audio samples are available at https://muzw.github.io/duramark_demo/.

eess.AS↗

arXiv2026

Dynamic Prosody Prediction in LLM-based TTS for Improving Speaker Similarity

Personalized text-to-speech (TTS) aims to clone the target speaker in the synthesized speech, imitating both the voice and speaking style. Current large language model (LLM)-based TTS methods ignore the style-specific prosodic patterns in generated speech, resulting in deficient style learning and thus limiting speaker similarity in synthesized speech. To this end, we investigate the prosody learning conditioned on the synthesized speech, and propose to predict the prosody of the current syllable based on previously predicted speech. Experimental results obtained on three datasets demonstrated the efficacy of the proposed dynamic prosody prediction method in enhancing the prosody learning capability, thereby improving the speaker similarity of the generated speech. Audio samples are available at https://muzw.github.io/dynapros/.

eess.AS↗

arXiv2026

An Ultra-Low-Bitrate Neural Speech Codec with Plain-to-Pseudo Synergistic Vector Quantization

Most neural speech codecs use residual vector quantization (RVQ), in which later VQs contribute less but consume the same bitrate, leading to inefficiency. We propose P2PSynCodec, an ultra-low-bitrate neural speech codec with a plain-to-pseudo synergistic vector quantizer (P2PSVQ). P2PSVQ consists of one plain VQ and multiple pseudo VQs. The plain VQ produces basic tokens by quantization, while the pseudo VQs generate auxiliary tokens by neural prediction and incur zero transmitted bitrate. Thus, speech is decoded from the plain-VQ tokens together with predicted pseudo-VQ tokens, greatly reducing bitrate. Experiments show that P2PSynCodec achieves speech reconstruction quality comparable to competing codecs at 2.0 kbps while operating at only 0.5 kbps, demonstrating high efficiency for ultra-low-bitrate speech coding.

eess.AS↗

arXiv2026

VoCodec: A Low-bitrate Streamable Neural Speech Codec with Voicing-driven Quantization

Neural speech codecs are key to speech transmission and storage, but most use uniform quantization across frames, allocating the same bitrate regardless of content and wasting bits. We propose VoCodec, a low-bitrate streamable neural speech codec with voicing-driven quantization that assigns higher bitrate to voiced frames and lower bitrate to unvoiced frames according to perceptual sensitivity. VoCodec embeds a voicing detector in a fully causal encoder-quantizer-decoder neural coding framework, using residual scalar-vector quantization for voiced frames and simple scalar quantization for unvoiced ones. Experiments show that on the LibriTTS dataset at a 16 kHz sampling rate, VoCodec outperforms baseline neural speech codecs even at a bitrate as low as 1.1 kbps. Our further experiments also confirm that introducing voicing-driven quantization can effectively reduce the bitrate by approximately 27% compared with uniform quantization strategy.

eess.AS↗