cs.SD · 2026-06-08 · No. 17
Sound, 2026-06-08.
8 new papers in cs.SD. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
8 entries-
01
Whisper Hallucination Detection and Mitigation via Hidden Representation Steering and Sparse AutoEncoders
Georgii Aparin, Vadim Popov, Tasnima Sadekova, Assel Yermekova
cs.SD · cs.AI
Whisper, a widely adopted ASR model, is known to suffer from hallucinations - coherent transcriptions generated for non-speech audio entirely disconnected from the input. We investigate whether hallucinations can be detected and mitigated through Whisper's internal representations. We extract audio encoder activations and evaluate two representation spaces: raw Whisper activations and Sparse AutoEncoder (SAE) latents. We show that both spaces...
-
02
How Far Can Chord-Symbol Time-Series Adaptation Carry Genre Identity? Capabilities and Boundaries in Multi-Genre Chord-Symbol Modeling
Jinju Lee
cs.SD · cs.LG
Harmony is a compact symbolic layer where mathematical pitch relations, acoustic consonance, and musical convention meet. This report treats chord-symbol sequences not as a complete representation of music, but as an interpretable, controllable time series for genre-local harmonic modeling. Starting from a frozen pop-jazz Music Transformer checkpoint, I evaluate how far small adaptation interfaces can extend the model to eleven target genres:...
-
03
Acoustic Cue Alignment in Audio Language Models for Speech Emotion Recognition
Iosif Tsangko, Andreas Triantafyllopoulos, Björn W. Schuller
cs.SD · cs.AI · cs.CL
Instruction-following audio language models (ALMs) can be augmented with explicit acoustic cues, yet it remains unclear whether such cues are used in a grounded way when the raw audio is already available. We study this question in speech emotion recognition (SER) by deriving six interpretable acoustic concept tokens from the standardised eGeMAPS paralinguistic feature set. These tokens summarise energy, pitch, dynamics, brightness, formants,...
-
04
TargetSEC: Plug-and-Play In-the-Wild Speech Emotion Conversion via Arousal-Conditioned Latent Style Diffusion
Constantin Alexander Auga
cs.SD · cs.LG
Speech Emotion Conversion (SEC) aims to transform the emotion of a source utterance into a target emotion while preserving content and speaker identity. SEC on in-the-wild data is challenging due to the non-parallel nature of training data and complex real-world acoustics. Existing fixed-duration approaches either struggle to shift the emotion effectively (high quality, low conversion) or degrade speech naturalness (low quality, high...
-
05
Entropy as a Structural Prior: How a Log-Barrier on DiT Belief Space Drives Musical Diversity and Development
Zixi Li, Youzhen Li
cs.SD · cs.LG · eess.AS
Confidence-based loss weighting is usually avoided in generative models because it accelerates errors when the model is confidently wrong, but this intuition breaks down in supervised diffusion training. We introduce the Eisbach log-barrier, a parameter-free weight derived from the entropy of the DiT output's spatial energy distribution: high entropy damps the gradient, while low entropy preserves it. Applied to LoRA fine-tuning of Stable...
-
06
dots.tts Technical Report
Shi Lian, Changtao Li, Bohan Li, Hankun Wang, Da Zheng, Junfeng Tian, Yufeng Ma, Colin Zhang, Kai Yu
cs.SD · cs.AI · eess.AS
We present dots.tts, a 2B-parameter continuous autoregressive text-to-speech (TTS) foundation model that models speech in a continuous latent space. Compared with existing continuous autoregressive models, our key innovations are threefold. First, we train an AudioVAE with multiple objectives to build a semantically structured and prediction-friendly continuous speech space. Second, we use full-history conditioning in the flow-matching head...
-
07
Phonetic Error Analysis of Raw Waveform Acoustic Models
Erfan Loweimi, Zhengjun Yue, Andrea Carmantini, Zoran Cvetkovic, Steve Renals, Peter Bell
cs.SD · cs.AI · cs.CL · cs.LG
We analyse error patterns of raw waveform acoustic models on TIMIT phone recognition beyond the overall phone error rate (PER). PER is decomposed across three broad phonetic class (BPC) categorisations, and confusion matrices are constructed from substitution errors. Our models combine parametric (SincNet, Sinc2Net) or non-parametric CNNs with Bidirectional LSTMs, achieving 13.9%/15.3% PER on Dev/Test, the best reported results for raw...
-
08
Towards Unified Song Generation and Singing Voice Conversion with Accompaniment Co-Generation
Ziyu Zhang, Chunyu Qiang, Xiaopeng Wang, Yuxin Guo, Kang Yin, Wenjie Tian, Jingbin Hu, Tianlun Zuo, Zhao Guo, Teng...
cs.SD · cs.AI
While song generation and singing voice conversion (SVC) have evolved significantly, they have long been developed isolated: the former lacks zero-shot speaker cloning, while the latter overlooks vocal-accompaniment synergy. To bridge this gap, we propose UniSinger, the first end-to-end framework unifying speaker cloning song generation and accompaniment co-generation SVC. Building on the multimodal diffusion transformer, we construct a...
This edition is part of The Daily Abstract — cs.SD archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.