arXiv_SD
-
Improving the performance of an ASV system using hybrid speech features
Abstract
The growing need for secure and convenient authentication methods has led to the increasing popularity of biometric solutions. In addition to traditional and popular methods, such as fingerprint or iris scanning, voice-based approaches are also employed. User identity verification based on voice is conducted using Automatic Speaker Verification (ASV) systems. Despite their many advantages, these systems are sensitive to various types of attacks and acoustic noises, which can reduce verification accuracy. This work examines the potential to improve the performance of ASV systems by using hybrid feature sets that combine different signal representations, starting with widely-used Mel-Frequency Cepstral Coefficients (MFCC), through Constant Q Cepstral Coefficients (CQCC) and ending with the innovative RAB descriptor. Experiments were conducted on recordings from the Google Speech Commands dataset under two scenarios: in clean conditions and in the presence of acoustic noise. Finally, the systems' performance was compared using the EER metric to determine whether hybrid feature sets decrease verification error. The results show that using a hybrid feature set (PNCC+RAB) improves speaker verification performance under noisy conditions.
Abstract (translated)
URL
https://arxiv.org/abs/2607.20706
PDF
-
Cumsum-Composable Phase Transport for Low-Cost Streaming Keyword Spotting
Abstract
State-space sequence models are attractive for streaming speech because they maintain compact recurrent state, but scan-style training kernels can have unfavorable constants for short audio tasks. We study cumsum-composable phase transport, a streaming-native temporal layer for keyword spotting. Each layer projects acoustic frames to complex channels, transports them by learned unitary rotations, accumulates a finite window using prefix differences, and applies a gated residual update. The same prefix representation gives exact batched training with ordinary cumulative sums and exact online inference with one prefix update per frame. Unitary transport is the key constraint: inverse rotations have norm one, keeping prefix terms well conditioned while memory is supplied by windows or block readouts. On Google Speech Commands v2 with 12 labels, mel+cumsum models retain competitive accuracy with compact baselines. The strongest single-seed run reaches 97.3\% test accuracy; a 51.6K-parameter tied model also reaches 97.3\%, and a 24.8K tied model reaches 96.8\% versus 97.1\% for a 25.6K MelCNNMaxPool baseline. In a matched cumsum-versus-scan benchmark, cumsum+window gives comparable accuracy, 94.82\% versus 94.33\%, while training 1.07x faster and reducing single-example latency from 7.09 ms to 5.01 ms on a Tesla T4. These results support cumsum phase transport as a simple low-cost temporal primitive for streaming keyword spotting.
Abstract (translated)
URL
https://arxiv.org/abs/2607.20086
PDF
-
What Affects the Performance of Fake Audio Detection? Analyzing Factors in a Continual Learning Setting
Abstract
The increasing sophistication of deepfake audio generation technologies makes it important to develop robust fake audio detection systems that can adapt over time. This study examines how various factors impact the performance of detection systems in a continual learning setting. We focus on factors such as attacker architectures, attackers' training datasets, speaker diversity, and task order. We evaluate the performance of three detection models trained with four different strategies, including direct fine-tuning, one-class classification, random replay, and Learning without Forgetting. Results show that artifacts from the fake audios might arise from the attackers' training datasets, and simply changing attacker architectures does not sufficiently challenge detection systems. Moreover, task order and speaker diversity can significantly influence performance, with varying degrees of sensitivity across different detection models and training strategies. These insights underline the need for careful consideration of these factors when developing robust detection systems.
Abstract (translated)
URL
https://arxiv.org/abs/2609.19067
PDF
-
Layer-Wise Decision Fusion for Fake Audio Detection Using XLS-R
Abstract
Recent fake audio detection methods often leverage large speech models to achieve robust speech representations. These models are typically very deep, providing multiple layer-wise representations. However, current works often rely solely on single layer representation or feature fusion to extract one utterance-level representation for decision making. These methods risk underutilizing rich information from multiple layers and might induce feature collapse. We propose a novel layer-wise decision fusion method that applies fusion after per-layer decision making and achieves the best cross-dataset performance on In-the-Wild dataset (EER 6.90%) compared to other strong baselines. Our model design also makes the model more transparent, allowing us to conduct detailed analysis to reveal the underlying mechanism of decision making.
Abstract (translated)
URL
https://arxiv.org/abs/2607.20023
PDF
-
Scalable Keyword Spotting via Modular Network Expansion
2026-07-22 08:48:13Viktor Khaymonenko, Dzmitry Saladukha, Aliaksei Rak, Alexander RostovAbstract
Keyword spotting (KWS) models on embedded devices often need to add new keywords after deployment, but updates are difficult when original training data are unavailable and regressions on existing triggers are unacceptable. At a fixed operating point, our method reduces average new-keyword false reject rate (FRR) from 6.46 to 4.37 versus a parameter-matched separate-model baseline and outperforms parameter-efficient tuning baselines (adapters, LoRA), while using fewer multiply-accumulate operations (MACs) under the same added-parameter budget ($\leq$10k): 16.34M vs 18.45M/20.52M. We achieve this via parameter-capped modular expansion: the base network, including batch-normalization statistics and the core classifier, is frozen, and only a lightweight expansion branch with a separate new-keyword head is trained, preserving core logits, shipped outputs, and thresholds for existing keywords.
Abstract (translated)
URL
https://arxiv.org/abs/2607.19918
PDF
-
StellarTTS: Sparse Temporal Embedding for Low-Latency and Robust Speech Synthesis
2026-07-22 07:48:37Kaicheng Luo, Xuefei Gong, Yutao Sun, Jinling He, Yujie Hou, Xiaoyang Xing, Huiyan Li, Bing Han, Yanmin QianAbstract
The trade-off between robustness, latency, and prosody critically challenges text-to-speech (TTS) systems. Autoregressive models, despite fidelity, are slow and error-prone; non-autoregressive (NAR) alternatives, while fast, often sacrifice prosodic naturalness via rigid alignments. This paper introduces StellarTTS, a novel mobile-optimized NAR TTS framework based on a sparse temporal embedding strategy, enabling granular control of phoneme duration, pronunciation, and prosody. Furthermore, we propose a semantic-aware codec that facilitates efficient single-stage decoding. Conditioned on the sparse temporal embedding, our 83M-parameter lightweight masked generative transformer achieves a real-time factor (RTF) of 0.08. Experiments demonstrate that StellarTTS attains lower latency and stronger robustness compared to state-of-the-art TTS systems, while maintaining competitive performance in audio quality, prosodic naturalness, and speaker similarity.
Abstract (translated)
URL
https://arxiv.org/abs/2607.19859
PDF
-
SimulS2ST-Omni: Data-Efficient Streaming Speech-to-Speech Translation via Explicit Trajectory Supervision
2026-07-22 06:42:20Rongshen He, Xinyu Liang, Dekun Chen, Jiaqi Li, Mingjie Chen, Zhizheng WuAbstract
Long-form streaming speech-to-speech translation (S2ST) requires incremental, unbounded translation under strict latency constraints. Existing methods typically suffer from sentence-bounded supervision or demand massive paired-S2ST supervision. We introduce a training recipe enabling a speech language model for sentence-level and long-form streaming S2ST using only $\sim$2k hours of paired cross-lingual S2ST data, layered atop auxiliary supervision. Anchored by auxiliary multitask training, our approach remains robust even when the paired-S2ST budget itself is reduced by 90\%. Our core contribution, joint text-code trajectory supervision, schedules target text and acoustic semantic codes as a unified commitment path, eliminating the need for separate, unstable speech-side emission controllers. Furthermore, our two-stream Thinker--Talker factorization significantly outperforms unified-decoder baselines by decoupling linguistic reasoning from dense acoustic prediction to mitigate modality interference. Finally, our system achieves highly competitive quality-latency trade-offs on RealSI and ACL60/60-dev, matching state-of-the-art, closed-source S2ST systems such as LiveInterpret~2.0 on ASR-BLEU.
Abstract (translated)
URL
https://arxiv.org/abs/2607.19810
PDF
-
Ultra-Compact CNN Architectures for Tropical Bird Audio Detection on Microcontrollers
2026-07-22 03:43:18Muhammad Mun'im Ahmad Zabidi, Mohd Yamani Idna Idris, Norisma IdrisAbstract
Passive acoustic monitoring of tropical biodiversity is bottlenecked by the storage and battery cost of continuously recording soundscapes in which bird vocalisations typically occupy less than 10% of the audio. Autonomous recording units built on low-power microcontrollers (typically ARM Cortex-M with $\leq$256 kB of RAM) address this by triggering only on likely-positive segments, but the on-device options are unsatisfying: coarse frequency-energy triggers such as Goertzel filters flood SD cards with false positives at $\sim$71% precision, whereas neural detectors developed for temperate single-species tasks are either too large to deploy or transfer poorly to species-rich tropical settings. We present DrongoNet, a family of three INT8 CNN detectors sized for this envelope and validated on a 50,000-clip, 1,677-species Southeast Asian tropical dataset (SEABAD). The headline model, DrongoNet-Micro (919 parameters, 6.26 kB, 0.9810 AUC, 98.3\% mean recall at {\tau} = 0.35), is a drop-in replacement for the Goertzel trigger used in commodity field recorders: at {\alpha} = 0.10 tropical prevalence it captures 8 pp more bird vocalisations than Goertzel and extends a 32 GB card from $\sim$28 to $\sim$45 days of monitoring. DrongoNet-Nano (5.09 kB) bounds the ultra-low-flash extreme; DrongoNet-Edge (33.06 kB, 0.9991 AUC) targets Linux SBCs. On SEABAD, Micro matches a retrained TinyChirp CNN-Mel baseline within 0.1 pp AUC at 28$\times$ fewer parameters, confirming that the family is deployment-agnostic across mel-spectrogram bird corpora but requires per-environment retraining. Full INT8 quantisation costs $<$0.12% AUC across all three variants.
Abstract (translated)
URL
https://arxiv.org/abs/2607.19721
PDF
-
A Diagnostic Evaluation Framework for AI-Generated Cover Songs Using Music-Theoretic and Acoustic Features
Abstract
AI-generated covers often fail through local musical errors that a global quality score cannot locate: the vocal contour may remain recognizable while the accompaniment uses the wrong harmonic function, or the output may stay in key while the arrangement remains incomplete. We present a five-dimensional diagnostic framework covering melodic pitch, harmonic progression, key consistency, style consistency, and arrangement/production quality. The benchmark contains 30 covers generated from 5 source songs by 6 systems, with expert severity ratings and 9 symbolic or acoustic features. Harmonic progression and arrangement had the highest severe-error rates (53% and 47%), whereas key consistency was better preserved. Six covers combined acceptable key consistency with severe harmonic errors. Large-leap ratio had a nominal association with melodic ratings (Spearman rho = -0.429, uncorrected p = 0.018), but no feature correlation survived the nine-test multiplicity reference. An interpretable percentile-rule pilot likewise failed to outperform a fixed majority baseline reliably across 16 dimension-level comparisons. The results separate useful diagnostic evidence from dependable automatic scoring: low-level and symbolic summaries can expose particular symptoms, but they do not replace context-aware musical judgment.
Abstract (translated)
URL
https://arxiv.org/abs/2607.19688
PDF
-
Black-Box Optimization for Identifying and Inverting Audio Dynamic Range Control Effects
2026-07-22 00:54:31Haoran Sun, Dominique Fourer, Hichem MaarefAbstract
Dynamic Range Compression (DRC) is a widely used nonlinear audio effect whose parameters are often unknown, making blind estimation and inversion challenging. In this work, we formulate DRC parameter estimation as a black-box optimization problem in a perceptually motivated feature space. Given an observed signal and a reference representation, we estimate the parameters that minimize the distance between feature descriptors of the reconstructed and reference signals. Unlike gradient-based approaches, the proposed method does not require differentiability of the DRC model or the feature extraction pipeline, enabling the use of nonlinear and histogram-based descriptors. Experimental results demonstrate that the proposed method achieves competitive performance in blind parameter estimation and dry signal recovery, outperforming or matching state-of-the-art models in terms of reconstruction quality.
Abstract (translated)
URL
https://arxiv.org/abs/2607.19645
PDF
-
RIME: Enabling Large-Scale Agentic Post-Production
Abstract
Almost every piece of recorded music you have ever heard was modified before it reached you; commercial releases rarely spring fully-formed from the mind of a musician. Despite the promise of music generation models for one-shot output, such fine-grained iterative refinement workflows are a complementary problem, and largely out of their reach. There is also a gap for musicians: while they can express what they want to hear, not all have the facility with studio production tools to implement the complex set of actions needed to realize these intuitions. We formalize this task as agentic post-production, wherein individual aspects of a song are targeted, refined, and combined into a final track. We argue the bottleneck is data: existing corpora do not reflect how realistic post-production chains map onto the vocabulary musicians and engineers actually use. We argue there is a language for modifying recorded music that is dense, consistent, and learnable. We introduce the Rule-based Instructions for Music Editing (RIME) framework, which generates realistic paired edit-instruction data from any baseline music dataset grounded in canonical methods, design patterns, and constraints derived from real production workflows. RIME leverages POEMS, a new toolkit that combines stem separation, mixing, and common studio effects for use by multimodal agents. We use RIME and POEMS to generate 3,000 pairs of edit instructions and ground truth audio, and use this data to evaluate existing multimodal LLMs as agents on this task, showing persistent challenges in current models' post-production capabilities. We also demonstrate RIME's ability to improve post-production agent performance via supervised fine-tuning. We see RIME as an early step toward iterative musical agents, collaborative systems that could transform music production much as interactive coding agents have reshaped software engineering.
Abstract (translated)
URL
https://arxiv.org/abs/2607.19605
PDF
-
Teleportation Game: Quantum Teleportation in Multi-Agent Systems for Interactive Music
2026-07-21 15:42:20Eduardo Reck Miranda, Scott Yeiichi OshiroAbstract
This paper introduces an interactive music system with quantum musical agents that communicate by teleporting quantum states to one another. Human performers interact in real time with agents whose melodic and rhythmic behaviours are encoded as quantum states using Single Qubit Probability Amplitude Modulation (SQPAM) and structured through Quantum Phase Estimation (QPE). Up to three agents are combined within a single quantum circuit, with directed communication via quantum teleportation. We are interested in supporting ambiguous, transformative interactions reminiscent of free Jazz improvisation. Therefore, rather than treating noise and decoherence as limitations, the system embraces NISQ-era constraints as creative affordances, framing agent communication as quantum whispers, that is, deliberate, musically expressive imperfections in state transfer. We provide demonstrations and analyses based on melodic correlation, pitch-set distance, and state fidelity, where a continuum between imitation and divergence can be observed. We developed a tunable interpretation method to assess how agents reinterpret teleported states. This work positions teleportation as a promising interaction mechanism for agent-based quantum computer music and outlines future directions toward distributed ensembles connected via the Quantum Internet.
Abstract (translated)
URL
https://arxiv.org/abs/2607.19212
PDF
-
Towards Array-Invariant Speech Enhancement via Geometry-Aware Dynamic Convolution
2026-07-21 03:02:57Zhenglong Liu, Wangyou Zhang, Chenda Li, Yanmin QianAbstract
Multi-channel speech enhancement (SE) systems exhibit superior performance over single-channel methods but are constrained to fixed microphone array configurations. This restricts their real-world deployment across devices with diverse array geometries. While recent array-agnostic SE methods address variable microphone numbers and permutations, they largely fail to exploit explicit array geometry priors when available, missing a crucial cue for optimal spatial filtering. A Geometry-Aware Dynamic Convolution (Geo-DConv) framework is proposed, which explicitly leverages microphone coordinates to transform standard fixed-array SE models into robust array-invariant systems. Experiments are conducted on the recent real-recorded RealMAN multi-channel speech dataset. Results demonstrate that the proposed architecture enables two widely used fixed-array models to adapt to array-invariant settings, with consistent performance improvements across diverse array topologies.
Abstract (translated)
URL
https://arxiv.org/abs/2607.18658
PDF
-
CAPS: A Cascaded Reconstruction Model to Power Saving in Hearables Using Sub-Nyquist Sampling with Bandwidth Extension
2026-07-21 02:09:58Tarikul Islam Tamiti, Sajid Fardin Dipto, Luke Baja-Ricketts, David Vergano, Anomadarshi BaruaAbstract
Hearables are wearable computers worn on the ear. Bone conduction microphones are used with air conduction microphones in hearables for multimodal speech enhancement in noisy conditions. Despite this potential, current models largely fail to explore how jointly reducing sampling bit resolution and sampling frequency in analog-to-digital converters (ADCs) of hearables impacts both power usage and audio quality. Furthermore, current frameworks cannot do sub-Nyquist sampling in hearables because they lack a method to reconstruct wideband signals from narrowband components. We therefore propose CAPS, which (i) intentionally employs sub-Nyquist sampling and low bit resolution in ADCs, achieving a 3.3x reduction in power consumption in hearables, and (ii) supports streaming operation on mobile platforms with an inference time of 1.36 ms and a memory footprint of 11.04 MB. CAPS ensures robust speech intelligibility in real-world settings, bridging the gap between efficiency and power savings.
Abstract (translated)
URL
https://arxiv.org/abs/2607.19434
PDF
-
CS-ETS: Chaos-Inspired Samba-Based EMG-To-Speech Synthesis with Nonlinear Chaotic Losses
2026-07-21 01:54:51Sajid Fardin Dipto, Tarikul Islam Tamiti, David Vergano, Luke Baja-Ricketts, Anomadarshi BaruaAbstract
We propose a chaos-inspired new architecture for EMG-to-Speech (ETS) synthesis called CS-ETS, which combines a Samba-based encoder with two novel chaos-inspired loss functions -- Lyapunov Exponent Regularization (LER) and Multi-Scale Detrended Fluctuation Analysis (MSDFA). LER is designed based on Lyapunov exponents to capture nonlinear fluctuations and sensitivity to initial conditions. MSDFA exploits detrended fluctuation analysis to quantify fractal-like, long-range temporal chaotic correlation. CS-ETS surpasses prior work with a 40.79\% lower parameter count (32M vs 54.1M) and introduces a new Post-Vocoder Alignment approach that improves LSD by 2.1x, STOI by 4.7x, and SI-SDR by 1.25x. CS-ETS reduces computation by 13.33\% while maintaining improved performance. To the best of our knowledge, for the first time, we show how ETS can be supervised by the subtle non-linear chaotic physics with Samba attention to achieve a significantly smaller model with superior performance.
Abstract (translated)
URL
https://arxiv.org/abs/2607.18629
PDF
-
End-to-End Markov State Sequence Learning for Auditory Attention Decoding
2026-07-21 01:33:59Yushan Yashengjiang, Jie Zhang, Miao Sun, Huadong Liang, Xin Li, Zhen-hua LingAbstract
Auditory attention decoding (AAD) identifies the speaker a listener attends to from neural responses like electroencephalography (EEG), making it a key algorithm in neuro-steered hearing aids. However, most neural AAD models are trained as independent short-window classifiers, despite auditory attention being a temporally persistent cognitive state and short-window EEG--audio evidence often being noisy and ambiguous. We propose an end-to-end Markov AAD framework based on conditional random field (CRF) that trains window-level neural emissions under a two-state attention prior. The framework treats the logits of any AAD backbone as Markov emissions, learns the transition rate from a standard HMM initialization, and jointly optimizes cross-entropy and CRF objectives, allowing temporal continuity to guide representation learning rather than merely smoothing predictions after training. We also introduce ESCNet, an EEG--speech correlation backbone that preserves time-aligned features and converts the difference between two mean Pearson correlations into state logits. We evaluate the framework with four emission backbones spanning correlation-based, convolutional, recurrent, and attention-based designs. On the dynamic AVGC dataset, CRF training generally outperforms post-hoc HMM smoothing; with ESCNet, it achieves $86.5\%$ causal and $92.4\%$ non-causal accuracy using $1$s windows. On the static KUL and USTC datasets, it improves causal decoding over fixed-rate post-hoc HMM baselines by $5.6\%$ and $2.0\%$, respectively, showing the superiority of learning AAD as attention state sequence over isolated-window classification.
Abstract (translated)
URL
https://arxiv.org/abs/2607.18614
PDF
-
Variable-Rate Harmonic-Percussive Time-Scale Modification with Real-Time Playback in Python
Abstract
Time-scale modification (TSM) has a number of open-source implementations, but these are designed almost exclusively for offline use, in which a recording is processed at a fixed rate and written out ahead of time. Applications such as automatic musical accompaniment require a different setting, which we call variable-rate playback: the recording to be stretched is known in advance, but the playback rate is not, and must change continuously in response to a live performer. The few implementations that generate output in real time are written in C++ and optimized for speed rather than for ease of modification, experimentation, and integration with the primarily Python-based research ecosystem. This paper describes a Python implementation of the widely used harmonic-percussive TSM method for the variable-rate playback setting. Harmonic-percussive separation is performed offline as a preprocessing step on the known input recording, while synthesis and playback are carried out in real time with a time-scale factor that may change at every frame. We further propose a family of variants that reduce runtime by replacing the phase vocoder's analysis-stage FFT and instantaneous frequency calculations with lookups into precomputed tables. Subjective listening tests with 24 participants (1114 pairwise ratings) show that these approximations become perceptually indistinguishable from the exact implementation once the precomputed hop size is sufficiently small, while reducing total runtime by roughly half. We characterize the resulting tradeoffs among precomputation, runtime, memory, and perceptual quality to guide algorithm selection, and we release our implementation as an open-source package.
Abstract (translated)
URL
https://arxiv.org/abs/2609.18999
PDF
-
Audio Cross Verification Using Dual Alignment Likelihood Ratio Test
2026-07-20 17:29:22Heidi Lei, Arm Wonghirundacha, Irmak Bukey, TJ TsaiAbstract
This paper explores a way to verify that audio has not been maliciously tampered in a specific context: short viral videos taken from news recordings. Rather than trying to detect artifacts of tampering (internal inconsistency), we focus on positively verifying a query against a trusted source such as a news recording (external consistency). We propose a method for cross verifying a short audio query against a reference recording from which it was taken. Our approach is to define two hypotheses (non-tampered vs tampered), calculate the most likely alignment between query and reference for each hypothesis, and then perform a likelihood ratio test on the two alignments. We show that this method is fast to compute, much more robust than using MFCC features with Euclidean distance, and has the key benefit of explainability. Our cross verification approach provides an alternative perspective and complementary tool to existing tampering detection methods.
Abstract (translated)
URL
https://arxiv.org/abs/2607.18190
PDF
-
Dense-Sparse Dynamic Time Warping for Customizing Piano Concerto Accompaniments
2026-07-20 17:29:10TJ Tsai, Kavi Dey, Yigitcan Ozer, Meinard MullerAbstract
In this study, we explore how pianists can customize Music Minus One (MMO) concerto accompaniments to match their playing style. Bypassing the need for a symbolic score, often not available digitally, we use three types of audio data: solo piano recordings, MMO orchestra-only recordings, and mixed recordings of both piano and orchestra (e.g., from YouTube). The mixed recording serves as an intermediary reference to align the solo and orchestra parts, with only the orchestral part being adjusted through time-scale modification to synchronize with the user's playing. The main challenge with estimating these alignments is the spectral mismatch between recordings containing different musical parts. Motivated by this application scenario, we introduce Dense-Sparse DTW, a variant of Dynamic Time Warping (DTW) that is designed to improve robustness of alignments to spectral mismatch by focusing on aligning a selected subset of audio frames containing prominent timing cues. We collect and annotate data from four piano concerto movements and establish a framework for generating and evaluating customized accompaniment recordings. On this benchmark, we show that Dense-Sparse DTW has better or comparable performance than more complex approaches based on source separation and spectral subtraction techniques.
Abstract (translated)
URL
https://arxiv.org/abs/2607.18189
PDF
-
Harness TTS: Towards Context-Aware Expressive Speech Synthesis with Harness Layer
2026-07-20 12:48:02Shengfan Shen, Di Wu, Xingchen Song, Dinghao Zhou, Pengyu Cheng, Sixiang Lyu, Jian Luan, Shuai WangAbstract
Expressive speech synthesis for voice assistants requires flexible style control that adapts to explicit requests and broader interaction context. We propose Harness TTS, a lightweight control layer that wraps around a TTS engine to externalize and govern its expressive behavior. It reformulates style control as closed-set prompt-tool routing: offline, a compact registry of stylistic prompt tools is constructed with structured metadata; online, an LLM planner selects the appropriate tool based on a priority-aware observation schema, and the TTS executor synthesizes speech using the corresponding prompt audio. We evaluate Harness TTS on both routing and synthesis tasks. In routing, Qwen3-4B achieves Top-1 accuracies of 74.3%, 43.0%, and 64.6% on explicit, implicit, and conflict subsets. For synthesis, experiments on CosyVoice3 and VoxCPM2 show that Harness TTS outperforms instruction-only control, achieving higher instruction-following win rates (margins of 23.1-35.6 points on CosyVoice3 and 13.8-20.0 points on VoxCPM2) and improving UTMOSv2 scores by 0.11-0.38. Moreover, the 4B planner delivers its first tool recommendation in under 50 ms in standard mode, introducing negligible latency for real-time interaction. These results demonstrate that equipping TTS engines with a dedicated Harness layer offers a practical, auditable, and context-aware solution for voice assistant expression control.
Abstract (translated)
URL
https://arxiv.org/abs/2607.17900
PDF
