arXiv_SD
-
The MPB Corpus: A Dataset of Melody, Rhythm, Harmony, and Melody-Harmony Relationships in Brazilian Popular Music
2026-08-14 00:17:10Carlos de L. Almada, Hugo T. de Carvalho, Felipe D. MartinsAbstract
This paper presents the MPB Corpus, a collection of 500 musical pieces encoded across four musical parameters: melodic contour, melodic rhythm, harmony, and the relationship between melody and harmony. It constitutes the most comprehensive and detailed dataset to date for computational musicology of Brazilian music. To support the encoding process, we introduce specific analytical models designed to capture rhythmic and melodic information with precision, alongside tailored visualizations and metrics summarizing key musical parameters. Finally, we provide a brief qualitative exploratory analysis of the dataset, illustrating its potential to both formulate and systematically address musicological questions concerning the genre.
Abstract (translated)
URL
https://arxiv.org/abs/2608.13842
PDF
-
Trajectory Dynamics in Self-Supervised Learning Latent Space for Audio Deepfake Detection
Abstract
Human speech production is constrained by physiology, giving rise to characteristic temporal structure on acoustic signals. We hypothesise that these constraints manifest as structured trajectory dynamics in the latent space of Self-Supervised Learning (SSL) models, and that synthetic speech violates them detectably. To test this hypothesis, we train a causal Long Short-Term Memory (LSTM) next-frame predictor on bonafide speech only (Stage 1), using the deepfake-specialised SSL backbone Wav2Vec2-Large-AntiDeepfake, and compare against a static global-average-pooling baseline using identical features, thus isolating the contribution of temporal modelling. A supervised Stage 2, which trains a Multi-Layer Perceptron on the frozen LSTM internal states using labelled data, is included to characterise the role of spoof supervision. Our system achieves competitive or state-of-the-art performance across six benchmarks: ASVspoof 2019/2021, Codecfake, In-the-Wild, MLAAD-EN, and Deepfake-Eval-2024, including best published EER on ASVspoof 2021 (0.75\%) and, notably, Stage 1 trained on bonafide speech only surpasses the published supervised baseline from the same backbone on DE2024 (30.35\%). On near-domain benchmarks, static and dynamic approaches perform comparably. On harder cross-corpus benchmarks with diverse synthesis methods, trajectory dynamics provide substantial gains, confirming that temporal physiological constraints carry detection signal beyond utterance-level statistics.
Abstract (translated)
URL
https://arxiv.org/abs/2608.13817
PDF
-
Architecture and Affordances of PLAUD: Performative Latents and Unsupervised DDSP
2026-08-13 19:36:47B{\l}a\.zej Kotowski, Frederic FontAbstract
PLAUD (Performative Latents and Unsupervised DDSP) is a neural synthesizer and Max for Live instrument for live electronic music, built on NoiseBandNet and trained on small personal sound corpora. We present its architecture, combining a variational DDSP synthesis model, latent smoothing, multi-scale spectral and adversarial losses, and an optional transformer prior, alongside a set of bending operations that intervene directly in the synthesis chain: component limiting, waveshaping, and prior feedback. The Max for Live interface exposes control generation, trajectory sampling, and modulation as primary modes of interaction. Throughout, we thread an affordance analysis arguing that the system's performative character follows from architectural decisions rather than being designed on top of them. The paper contributes both a technical account of the system and a situated affordance analysis of its role in live electronic music performance.
Abstract (translated)
URL
https://arxiv.org/abs/2608.13724
PDF
-
VoxAudio: Vocalized Audio Synthesis via Multi-Reward Autoregressive Flow Matching
2026-08-13 08:27:22Wenxiang Guo, Changhao Pan, Ziyue Jiang, Fei Wu, Zhou ZhaoAbstract
Vocalized audio synthesis, the task of generating audio in which intelligible speech is embedded within an environmental soundscape, underpins applications such as podcast production and video dubbing. Existing Text-to-Audio (T2A) systems either reduce quoted speech to unintelligible vocal murmur or delegate it to a separate TTS model with post-hoc mixing, which forfeits control over when speech occurs and how it interacts with the scene. We present VoxAudio, a causal autoregressive flow matching model that addresses this problem from three complementary aspects. At the architecture level, chunk-wise causal factorization with independent per-chunk noise levels lets audio be emitted through sliding-window streaming inference with KV caching at variable target durations; to enable inference at arbitrary chunk granularities, we further pretrain the model with randomized chunk boundaries. At the preference level, multi-reward Negative-aware FineTuning (NFT) jointly optimizes semantic fidelity, linguistic accuracy, aesthetic quality, and temporal grounding At the data level, to supply the missing supervision for vocal content, we build VoxCorpus, a large-scale corpus whose captions quote the verbatim transcript of embedded speech with time intervals, and VoxBench, an interval-annotated benchmark with a temporal-grounding metric. Experiments on four benchmarks spanning general audio, speech, and unified vocalized audio validate the effectiveness and efficiency of VoxAudio. Our code and demos are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2608.12951
PDF
-
SceneTTS-Bench: A Benchmark for Scene-Level TTS in Drama Dubbing
2026-08-13 07:27:38Yizhong Geng, Yanliang Li, Jinghan Yang, Tianhan Jiang, Yingming Gao, Ya LiAbstract
Text-to-speech systems are increasingly used for drama dubbing, yet evaluation protocols remain sentence-level, leaving critical scene-level behaviors insufficiently measured. We present SceneTTS-Bench, a benchmark that evaluates TTS along three dimensions: timbre consistency across character turns, emotional expressiveness on high-tension utterances, and rhythm coherence under segmented long-form synthesis. The corpus comprises real-world and generated drama scripts totaling 160 bilingual scenes and approximately 10,300 utterances, with real-world scripts serving as the primary source (100 scenes) and generated scripts as a supplementary source (60 scenes), demonstrating the framework's extensibility through synthetic data augmentation. A backend-agnostic Canonical Intermediate Representation ensures fair cross-system comparison. Three automatic pipelines produce per-utterance diagnostics: Speaker Consistency Score for timbre-drift detection, Under-Acting Ratio for under-acting identification, and Rate Discontinuity Ratio for rate-discontinuity quantification. Experiments on four TTS systems confirm that each system exhibits distinct weaknesses and that scene-level rankings diverge substantially from sentence-level metrics. Benchmark resources are publicly available at this https URL .
Abstract (translated)
URL
https://arxiv.org/abs/2609.26255
PDF
-
Alignment Drift in Single-Model Speculative Decoding for ASR: Mechanism, Correction, and Cost
2026-08-13 01:34:38Xinyu Wang, Huapeng Zhou, Ziyu Zhao, Silin Meng, Ke Bai, Dongming Shen, Xiao-Wen Chang, Alex SmolaAbstract
Speculative decoding speeds up generation by letting a cheap draft propose several tokens that a target model checks in one pass. In the single-model form, the draft is a lightweight module attached to the target rather than a separate model. Applying this design to Automatic Speech Recognition (ASR) introduces an extra problem. The draft can read the whole audio at every step, yet its proposals get worse as it runs on its own. Access is not localization. The accepted text keeps the transcript position explicit, but the draft must also track the changing audio position. In the primary matched comparison, per-step audio access changes the first proposal modestly but roughly doubles later-proposal acceptance. Fixed-width windows show that the audio position explains part of this gap. A correctly placed window recovers continuation, while an equally narrow window at the wrong position reduces it. Late-draft median error reaches 21 frames in the hardest reported condition, while target attention during verification stays within a 2-frame median. We test two ways to reduce this drift. The first reads the audio position from verification attention and uses it to guide the next draft round. It saves time only when the extra accepted tokens offset the readout cost. The second is AnchorDraft, which teaches the draft to track the audio position during training without changing the inference graph. The trained draft improves end-to-end speed at both tested target scales. These results show that ASR self-speculation depends on token prediction, audio-position tracking, and draft cost.
Abstract (translated)
URL
https://arxiv.org/abs/2608.12703
PDF
-
Drive-to-Music: Context-Aware Generative Audio for In-Vehicle Experiences
Abstract
In-vehicle music can serve as an adaptive interface to enhance driver experience, attention, and well-being. We present Drive-to-Music, a context-aware system that generates music in real time from multimodal driving signals. Using dashcam imagery and vehicle telemetry, the system extracts scene semantics and driving context, maps them to high-level musical descriptors, and conditions generative audio models to produce contextually aligned soundtracks. The architecture combines perception and generative components to translate visual and kinematic inputs into structured musical attributes and synthesize audio with low latency. It supports smooth transitions as driving conditions evolve, and to ensure robustness and deployment readiness, we incorporate constraint-based controls and safety checks across the generation pipeline. Our results demonstrate the feasibility of real-time, context-aware music generation in automotive settings, providing a foundation for personalized and adaptive in-vehicle audio experiences.
Abstract (translated)
URL
https://arxiv.org/abs/2608.12615
PDF
-
The SLT 2026 SmartGlasses Challenge: Benchmarking Egocentric Multi-Talker Speech Recognition and Understanding with Audio-Language Models
2026-08-12 13:18:49Dehui Gao, Zhixian Zhao, Zhennan Lin, Yujie Liao, Yuhang Dai, Yike Zhu, Longshuai Xiao, Hui Bu, Xin Xu, Xie Chen, Shuai Wang, Liumeng Xue, Zhonghua Fu, Jun Du, Eng-Siong Chng, Jun Zhou, Lei XieAbstract
Recent advances in large language models (LLMs) and multimodal LLMs (MLLMs) have created new opportunities for wearable speech interfaces, with smart glasses providing an egocentric platform for continuous audio sensing and assistance. However, speech recognition and understanding in this setting remain challenging because of dynamic acoustic conditions, speaker overlap, and the spatial ambiguity introduced by wearer-centered recording geometry. To support systematic evaluation in this setting, we introduce the IEEE SLT 2026 SmartGlasses Challenge for egocentric multi-speaker speech processing. The challenge consists of two tracks, Dyadic Dialogue Understanding and Multi-party Meeting Understanding, and jointly evaluates Time-Stamped Speaker-Attributed Automatic Speech Recognition (TSA-ASR) and Spoken Language Understanding (SLU). It is built on a 106-hour four-channel egocentric speech dataset containing 714 sessions collected in real-world scenarios. This paper describes challenge tasks, dataset construction, submissions, and summarizes the main findings from the shared evaluation. The results show that heavy speaker overlap remains a major factor affecting TSA-ASR performance, while paralinguistic acoustic understanding continues to be difficult for current audio-language models in complex SLU settings. Further details can be found on the official challenge website.
Abstract (translated)
URL
https://arxiv.org/abs/2608.12034
PDF
-
Do Text-to-Music Models Really Follow Instructions? A Counterfactual Evaluation of Key and Beat Grouping
Abstract
Prompted attribute agreement is widely used as evidence of text-to-music controllability, yet a requested attribute may occur simply because it is already common in the model's output distribution. We introduce a matched counterfactual evaluation that separates target occurrence from instruction-attributable control. Each family contains a neutral input that omits the scored attribute and two otherwise matched inputs that swap the requested target. All three are rendered through frozen native-interface adapters with a shared seed. Applied to global key and beat grouping in three open systems, this design changes the empirical conclusion. ACE-Step 1.5 and Stable Audio 3 Medium exhibit substantial key control, whereas LeVo2 does not. For beat grouping, the same models redirect toward the rare three-beat target, but high four-beat agreement is largely inherited from neutral outputs: Stable Audio 3 produces four-beat grouping in 0.97 of neutral cases but only 0.56 under its explicit four-beat treatment. Off-attribute placebos, external recognizer validation, blind expert annotation, and multi-seed sentinels support the attribution. When targets have unequal output priors, agreement describes what a model produced, while matched neutral and target-swap contrasts test whether the instruction changed it.
Abstract (translated)
URL
https://arxiv.org/abs/2608.11899
PDF
-
MiDashengLM-Gen: Unified Audio Scene Generation via LLM-Driven Autoregressive Flow Matching
2026-08-12 08:46:28Xingwei Sun, Heinrich Dinkel, Gang Li, Jiahao Mei, Yadong Niu, Zerui Han, Yuepeng Jiang, Jiahao Zhou, Lichun Fan, Jian LuanAbstract
Generating coherent audio scenes that simultaneously blend speech, music, and sound effects remains a significant challenge. Current approaches typically rely on a disjointed pipeline where a frozen, decoupled text encoder feeds a separate audio decoder, limiting cross-modal optimization and leading to poor speech intelligibility. To overcome these limitations, we introduce MiDashengLM-Gen, an end-to-end framework that couples a pre-trained Large Language Model (LLM) with per-token conditional flow matching for autoregressive, variable-length mixed-audio scene generation. MiDashengLM-Gen represents a first approach for general text-to-audio generation with one end-to-end trained model. Empirical evaluations demonstrate that MiDashengLM-Gen drastically improves speech intelligibility over existing unified models. On the Seed-TTS benchmark, English Word Error Rate (WER) drops from 12.15% to 2.79%, approaching the performance of dedicated Text-to-Speech (TTS) systems (1.24%). Furthermore, the framework extends effectively to multilingual settings, yielding highly competitive multilingual WERs compared to existing baselines. Lastly, the model maintains competitive mixed-audio generation quality on the MECAT benchmark. Code and checkpoints are available at this https URL and this https URL, and the demo page is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2608.11804
PDF
-
Phoenix TTS: High-Fidelity Synthesis and Voice Conversion via Flow-Matching-Driven Speech Tokenization
2026-08-12 07:23:54Peijie Chen, Zhuanling Zha, Zhipeng Nie, Weijie Wu, Yiming Liu, Daiyu Huang, Junbo Li, Jun Fang, Naiqiang Tan, Hua Chai, Qingyang HongAbstract
In current zero-shot text-to-speech systems, conventional semantic tokenizers are typically optimized using supervised automatic speech recognition or self-supervised learning objectives. However, due to the inherent nature of speech, semantic and acoustic information cannot be completely decoupled, and ASR-based tokenizers discard acoustic details to focus on linguistic content; models relying on them usually struggle to achieve optimal speaker similarity. Furthermore, these tokenizers are optimized independently and lack direct supervision from downstream acoustic generation tasks. This isolated training creates a feature gap between the extracted discrete tokens and the continuous space required by acoustic models, fundamentally bottlenecking the upper bound of synthesis quality. To bridge this gap, we propose Phoenix TTS, a unified framework that tightly couples representation learning with generative acoustic modeling. Specifically, our speech tokenizer is optimized to reconstruct self-supervised features to maintain semantic richness, while simultaneously receiving direct supervision from a Flow Matching training loss. Through this joint training paradigm, the extracted discrete tokens successfully preserve essential semantic information and natively align with the feature space of the downstream Flow Matching model. Comprehensive evaluations highlight the efficiency and effectiveness of Phoenix TTS. Trained on 110K hours of data, the system achieves excellent speech intelligibility, yielding WER that consistently falls below that of ground-truth recordings. Simultaneously, it maintains robust zero-shot speaker similarity, rivaling or outperforming several prominent large-scale baselines. Furthermore, as an advantageous byproduct of this unified training, the learned tokenizer can be seamlessly adapted to zero-shot voice conversion tasks without requiring task-specific fine-tuning.
Abstract (translated)
URL
https://arxiv.org/abs/2608.11737
PDF
-
Luna-TTS Family Technical Report
2026-08-12 03:07:07Feng Yin, Shuai Shi, Junjie Zheng, Kechenying Zhou, Yiqiu Wang, Chenyang He, Qiuhua Jiang, Mengxiao Bi, Yanmin Qian, Mingxin Chen, Xun Gong, Tianteng Gu, Bing Han, Peng Jiang, Chenda Li, Haiyang Sun, Han Wang, Wei Wang, Yi Wang, Leying Zhang, Wangyou Zhang, Chushu ZhouAbstract
Modern text-to-speech (TTS) is dominated by autoregressive (AR) codec language models, whose left-to-right decoding brings latency that grows with utterance length, error accumulation along the committed prefix, and an artificial generation order imposed on the Residual Vector Quantization (RVQ) token grid. We propose Luna-TTS Family, diffusion-language-model-based TTS systems pretrained on 1 million hours of speech across Chinese, English, Japanese, and Korean. The family is built by progressive adaptation of a pretrained AR text LLM, from causal to bidirectional and finally to block-causal attention, and comprises two variants sharing a single tokenizer, data pipeline, and 0.6B backbone lineage. Luna-TTS is fully non-autoregressive: it generates the entire RVQ token grid in a fixed number of parallel refinement steps, with zero-shot voice cloning and speech editing arising natively as infilling. Luna-TTS Realtime, derived by continual training, is autoregressive over blocks of 32 codec frames (1.28s) while denoising each block in parallel; it supports KV-cached blockwise generation and incremental audio delivery, achieving an end-to-end RTF of 0.0240 and 41.6 ms local first-block latency under the warmed serving protocol. An annealed fine-tuning stage adds explicit control over emotion and non-verbal vocalizations (NVVs), and a reinforcement-learning stage applies GRPO with policy ratios computed over the realized denoising trajectory. On Seed-TTS-Eval, Luna-TTS achieves the best results on all four metrics among compared open-source and commercial systems (0.73 CER / 79.7 SIM on test-zh, 1.49 WER / 76.8 SIM on test-en); on the harder in-the-wild CV3-Eval, it posts the lowest Mandarin and English error rates in our comparison. Against leading commercial systems, it achieves the best results on most objective, model-based, and human-rated metrics for NVV and emotion control.
Abstract (translated)
URL
https://arxiv.org/abs/2608.11593
PDF
-
CookVoice: Unified Framework for Style Controllable Multi-Modal Human Voice Generation
2026-08-12 02:58:45Haowei Lou, Hye-Young Paik, Dai Jia, Kai Li, Lina YaoAbstract
Human voice generation has made rapid progress in speech generation, singing voice generation, voice cloning, and voice editing. However, most existing systems are designed for specific tasks and often rely on task-dependent architectures, control signals, or autoregressive decoding, limiting fine-grained controllability and inference efficiency. In this paper, we propose CookVoice, a unified framework for multimodal, multi-style, and multi-task human voice generation. CookVoice decomposes the human voice into three key factors: content, prosody, and style, enabling both speech and singing voice generation within a unified model. To achieve precise and flexible controllability, we design a flexible alignment strategy that maps text, style, and prosody control signals onto the frame-level of spectrogram. This design allows CookVoice to support a wide range of tasks, including text-to-speech, text-to-singing voice, style-controllable generation, voice mimicry, voice conversion, and voice editing. Experimental results show that CookVoice achieves generation quality comparable to existing Text-to-Speech and text-to-singing voice baselines, while providing stronger style and prosody controllability. Moreover, CookVoice achieves comparable performance to large-scale baselines with only 43.51 million parameters and efficient inference using as few as 4 ODE steps, making it a practical solution for real-world human voice generation applications. Demo page is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2608.11590
PDF
-
Measuring Cross-Cultural Style Diffusion Through Era Classification: US and Korean Popular Music
2026-08-11 14:36:01Dasol Lee, Minhee Lee, Seonguk Ju, Daewoong Kim, Harin Lee, Dasaem JeongAbstract
Popular music circulates globally while being locally reinterpreted, yet this process of cross-cultural style diffusion has rarely been quantified. We propose an era-classification framework for measuring temporal alignment between chart cultures. CNN classifiers trained from scratch on Billboard Hot 100 audio are applied to Korean Melon chart songs. Korean chart songs from the 1960s through the 1980s are consistently inferred as belonging to earlier Billboard eras, by a median of about four to five years, while the same models remain unbiased on held-out Billboard audio. The offset then halves at the 1990s, to roughly two to three years, and holds there through the 2000s. Reverse inference shows a complementary narrowing, and the pattern holds across architectures and seeds. We interpret these results as reflecting how globally circulating pop styles were locally adopted and progressively synchronized. The framework can be applied to other pairs of chart cultures beyond the US-Korea case examined here.
Abstract (translated)
URL
https://arxiv.org/abs/2608.10980
PDF
-
Pitch Contour Tokenization using VQ-VAE and Its Application on Korean Traditional Music Analysis
2026-08-11 14:35:43Seonguk Ju, Seola Cho, Sooin Chung, Danbinaerin Han, Dasaem JeongAbstract
Computational analysis of music often relies on discrete representations, yet many musical traditions are organized around continuous pitch movement that resists segmentation into note-like units. For such traditions, the discrete units that analysis would build on are not given in advance. We address this gap by learning a vocabulary of local pitch-contour patterns directly from unlabeled audio, using a VQ-VAE that quantizes fixed-length contour segments into a finite codebook. To make the learned tokens stable across segmentation positions and small variations in timing and pitch range, we train the model with a reconstruction objective evaluated under the best alignment among a set of candidate temporal and pitch-domain transformations. Applied to Korean traditional music, the learned tokens recover information about expert-defined sigimsae categories without supervision, and in pansori individual tokens align with the two principal modes, Gyemyeonjo and Ujo, supporting their use as units for corpus-level analysis of contour-centric traditions.
Abstract (translated)
URL
https://arxiv.org/abs/2608.10979
PDF
-
DINO-A: Adapting Self-Distillation Vision Transformers to General Audio Representation Learning
2026-08-11 08:43:16Tomasz Radzikowski, Mateusz Modrzejewski, Przemys{\l}aw RokitaAbstract
We present DINO-A, an adaptation of self-distillation from vision to general audio representation learning. While DINO has become a canonical method in self-supervised vision and prior audio work has explored latent prediction (BYOL-A) and masked modeling (Audio-MAE, BEATs), no prior work has brought canonical DINO to general audio classification in the way BYOL-A brought BYOL. DINO-A retains DINO's multi-crop, EMA teacher, and high-dimensional projection, replacing only the input modality and augmentations with log-mel spectrograms and the BYOL-A v2 augmentation block. We pretrain three backbones, two Vision Transformers with 8x8 and 16x16 patches and a convolutional encoder, on FSD50K and evaluate them with linear probing on ESC-50, Speech Commands v2, UrbanSound8K, and GTZAN. Three findings characterize the resulting representations. Patch resolution within the Vision Transformer family has consistent effect on representation quality, with smaller patches winning across all four tasks. The choice between Vision Transformer and convolutional backbone interacts with task type: convolutional networks lead on speech while Vision Transformers lead on environmental sounds and music. Under identical pretraining and evaluation conditions, DINO-A and BYOL-A v2 differ by 11.96 percentage points on average, and we trace this difference to two mechanisms: the interaction between DINO's high-dimensional projection space and FSD50K's limited scale, and the additional cost of multi-crop augmentation, which DINO uses but BYOL-A v2 does not. The high-dimensional projection space, central to DINO's success in vision, becomes a liability at FSD50K scale.
Abstract (translated)
URL
https://arxiv.org/abs/2608.10659
PDF
-
Beyond Dry References: Learning Relative Audio Effects Representations via Contrastive Distance Learning
2026-08-11 07:00:35Xinlu Liu, Huibin Lin, Weixing Wei, Zhenhai YanAbstract
Audio effects (Fx) representation learning plays a key role in intelligent music production, including automatic mixing and Fx style transfer. Existing methods typically rely on dry or nearly dry references for effect modeling, yet truly unprocessed audio is rarely available in practice, as real recordings inevitably reflect the microphone, room acoustics, and preceding signal processing. Instead of pursuing absolute effect encodings, we argue that the relative effect distance between audio signals is more meaningful for real-world music production. Motivated by this, we propose RelFx, a contrastive learning framework that learns relative effect transformations from general audio collections without requiring dry references during representation training. Our approach uses a dual-branch Siamese encoder equipped with cross-attention and differential gating fusion to infer the shared effect transformation from a reference clip and an effect-processed, content-related clip. We further propose an antisymmetric fusion variant for bidirectional effect encoding, such that swapping the input order directly produces a nearly sign-reversed embedding, a property not explored in earlier work. Moreover, our dry-reference-free formulation eliminates the reliance on dry multitrack datasets and enables training on effect-bearing audio. Experiments on Fx style transfer demonstrate state-of-the-art performance under the standard Fx-Encoder++ MUSDB18 evaluation protocol, consistently outperforming existing approaches across all four instrument categories.
Abstract (translated)
URL
https://arxiv.org/abs/2608.10573
PDF
-
TTS-Q: Perception-Guided Post-Training Quantization of Text-to-Speech Diffusion Transformers
2026-08-11 00:27:07Xiaoqin Feng, Yuqi Li, Weilun Feng, Yi-Cheng Lin, Kai Li, Xianglong Wang, Kuo Yang, Chuanguang Yang, Yingli Tian, Wei Li, Zhongwei Cheng, Lin ChenAbstract
Zero-shot text-to-speech (TTS) can clone a voice from seconds of audio. Yet the quality comes from billion-parameter diffusion transformers whose size and multi-step sampling put them out of reach of the on-device, assistive, and real-time applications that need them most. Post-training quantization (PTQ) shrinks such models without retraining, but it has been built for language and vision, not speech. At 4 bits, a strong quantizer leaves intelligibility close to full precision but consistently erodes speaker timbre, so error rates stay low while the voice drifts from the target speaker. We ask why quantization hurts speech, where the damage lives, and whether it can be repaired without retraining. To find out, we run the first 4-bit weight-and-activation (W4A4) PTQ study of a TTS diffusion transformer at 1B and 3.5B. The timbre cost comes from both the weight and the activation quantization, but only the activation part has the timestep structure a precision schedule can exploit. We therefore introduce TTS-Q, which selects hard-to-quantize items from task-matched calibration candidates and applies a budget-balanced mixed-precision schedule that assigns higher precision to late-step feed-forward activations. TTS-Q recovers timbre best at both scales, at no cost to intelligibility. Separately, the deployed calibrated-W4A4 reference reduces peak memory on GPU, providing a practical reference for resource-constrained TTS deployment.
Abstract (translated)
URL
https://arxiv.org/abs/2610.12474
PDF
-
DIY e-HandPan: A new DIY Low-Cost Handpan Interface based on Arduino and ESP32 Microcontrollers
Abstract
We present DIY e-HandPan, a new open-source, low-cost and customizable handpan audio and MIDI protocol interface designed for musical performance, education and research. The proposed hardware is built from inexpensive electronic components and recycled materials using widely available fabrication techniques, making it accessible to makers, educators and researchers. The instrument can be implemented on two distinct MicroController Unit (MCU): Arduino or ESP32. The microcontroller captures strike velocity to provide expressive musical performance comparable to that of an acoustic handpan. In addition to real-time audio and MIDI generation, DIY e-HandPan integrates a bi-color LED guidance system capable of displaying musical sequences from MIDI files, providing an effective learning aid for beginners and educational activities. The modular architecture allows users to easily customize the number of notes, hardware configuration and embedded software according to specific applications. We present the complete hardware design, firmware and assembly instructions and we discuss the design choices and limitations, to evaluate the system in representative educational and musical performance scenarios. All design files, source code and documentation are released under an open-source license to improve the reproducibility and encourage further developments by the open hardware community.
Abstract (translated)
URL
https://arxiv.org/abs/2608.10185
PDF
-
Monophonic Audio Synthesizer Using FPGAs
Abstract
Signal synthesis is used in every aspect of the electronics world, where sinusoidal waveforms are used to perform functions such as clocking, signal transmission, feedback controls, and other applications. Digital synthesis is the method of approximating sinusoidal waveforms using digital logic, where the waveform is approximated to an accurate degree at a specific frequency which can be either implemented digitally or converted into the analog domain for use elsewhere. This project details the creation of a digital synthesizer commonly used for professional audio applications through the implementation of hardware in an FPGA.
Abstract (translated)
URL
https://arxiv.org/abs/2608.10116
PDF
