2026-11-18 | CS.SD语音与音频 | 共 4 篇
[机构]信息由AI分析生成,可能存在错误,仅供参考,以论文实际显示为准
快速导航
1. 语音识别与关键词检测 1 篇
2. 语音合成与声音生成 1 篇
3. 语音增强、降噪与音频修复 1 篇
4. 音乐信息检索与音乐生成 1 篇
1. 语音识别与关键词检测 | 1 篇
1. Beyond Mimicry: Constrained Exploration with GRPO for Joint Multi-Talker ASR and Diarization under Unknown Speaker Counts
超越模仿:在未知说话人数量下,采用GRPO的受限探索用于联合多说话人ASR与说话人 diarization
AI 总结:该研究针对未知说话人数量下的联合多说话人ASR与说话人 diarization问题,提出含CoT增强SFT和GRPO受限探索的两阶段框架,在Libri3Mix等数据集上显著降低了cpWER。
链接:https://arxiv.org/abs/2611.22627
机构:The Chinese University of Hong Kong(香港中文大学); Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院)
作者:Yunrui Cai, Dingdong Wang, Lingwei Meng, Xixin Wu, Zhiyong Wu, Helen Meng
英文摘要:Joint multi-talker ASR with speaker attribution and timestamps is particularly challenging when the speaker count is unknown and the output must follow a strict structure. We observe that Supervised Fine-Tuning (SFT)-only alignment of SpeechLLMs is brittle under dense overlaps, often leading to burst hallucinations and malformed speaker/timestamp tags. We propose a unified two-stage generative framework: (i) CoT-augmented SFT that infers the global speaker count before transcription, and (ii) GRPO-based constrained exploration guided by a Multi-dimensional Constraint-Aware Reward (MCAR) that directly optimizes permutation-invariant accuracy while enforcing counting, temporal, and structural constraints. On Libri3Mix and a Dynamic-Mix (2+3) set (speaker count unknown at test time), our model achieves 14.52%/9.24% cpWER and 1.95%/1.12% WDER, respectively, with GRPO yielding a 35%/54% relative cpWER reduction over SFT+CoT.
2. 语音合成与声音生成 | 1 篇
2. High-Fidelity Binarized Neural Vocoder
高保真二值化神经声码器
AI 总结:针对神经声码器推理成本高的问题,提出面向BNN的BiVoC声码器,适配RNDVoC框架并采用混合精度设计,在低计算成本下实现高保真波形生成,性能优于直接二值化的声码器。
链接:https://arxiv.org/abs/2611.22593
机构:Institute of Acoustics, Chinese Academy of Sciences(中国科学院声学研究所); University of Chinese Academy of Sciences(中国科学院大学); Tencent(腾讯)
作者:Andong Li, Tong Lei, Xiaodong Li, Chengshi Zheng
英文摘要:Neural vocoders have achieved remarkable progress in high-fidelity waveform generation in recent years, but most existing methods still rely on full-precision operators, leading to non-negligible storage and computational costs during inference. Binary neural networks (BNNs) provide an alternative direction by quantizing weights and activations to 1 bit. However, directly applying binarization to neural vocoders is rather challenging as it inherently incurs severe information loss. To this end, we propose BiVoC, a BNN-oriented time-frequency neural vocoder for high-fidelity waveform generation. Building on our previous full-precision RNDVoC framework, BiVoC adapts the inverse-problem formulation, range-null decomposition, and fineto-coarse non-uniform subband modeling to the 1-bit setting. Specifically, we develop a simple binarized convolutional unit to provide stable time-frequency feature modeling under binary representations. Furthermore, we analyze the quality-complexity sensitivity of different modules and propose a mixed-precision design to retain quality-sensitive components in full precision while binarizing computation-dominant parts. Extensive experiments are conducted on LibriTTS and multiple out-of-distribution benchmarks. Both objective and subjective results demonstrate that BiVoC substantially outperforms BNN variants obtained by directly binarizing existing vocoders, while achieving competitive performance against several mainstream full-precision vocoder baselines under much lower theoretical computational cost. These results demonstrate the promising potential of BNNs in the audio generation field. Codes and pre-trained weights are available at this https URL.
3. 语音增强、降噪与音频修复 | 1 篇
3. Back to Mel: Learning to Bridge Fidelity and Perception in Generative Speech Enhancement
回归梅尔频谱:学习弥合生成式语音增强中的保真度与感知质量
AI 总结:本文提出基于流匹配的BAME框架,通过子带感知Transformer、相位感知神经声码器及单步保真度-感知对齐策略,在多个基准上实现了高效且性能优异的生成式语音增强。
链接:https://arxiv.org/abs/2611.22628
机构:Institute of Acoustics, Chinese Academy of Sciences(中国科学院声学研究所); University of Chinese Academy of Sciences(中国科学院大学); Laboratoire de Traitement et Communication de I’Information (LTCI), Télécom Paris, Institut Polytechnique de Paris(巴黎综合理工学院电信学院信息处理与通信实验室(LTCI))
作者:Andong Li, Kun Zhou, Xiaodong Li, Chengshi Zheng
英文摘要:Recent generative techniques have facilitated the rapid proliferation of speech enhancement approaches built upon learnable compact latent representations and large generative backbones. Nevertheless, it remains inherently challenging to balance between acoustic fidelity, perceptual quality, and processing efficiency. In this paper, we revisit the Mel spectrum as a structured acoustic representation and propose BAME, a flow-matching-based framework that exploits the complementary priors for generative speech enhancement task. First, leveraging the explicit hierarchical frequency distribution of Mel spectrum, we elaborately devise a subband-aware Transformer (SaT) for efficient generative modeling. Using only 2.9% of the parameters, the proposed SaT achieves superior enhancement performance compared with a 331 M DiT backbone. Second, motivated by range-null decomposition theory of Mel filtering in the magnitude-spectral domain, we introduce a phase-aware neural vocoder that incorporates degraded-phase prior, together with a quality-guided dual-phase strategy to adaptively mitigate the effects of unreliable phase information. Third, we devise a simple yet effective one-step fidelity-perception alignment strategy that fine-tunes the flow model with complementary constraints from fidelity and perception domains. Extensive experiments are conducted on DNS-Challenge, EARS, GSR, and URGENT benchmarks, and both objective and subjective results demonstrate promising performance on various intrusive and non-intrusive evaluation metrics. These results further advocate the potential of exploiting structured acoustic representations for reliable and efficient generative speech enhancement. Audio samples and codes are available at this https URL.
4. 音乐信息检索与音乐生成 | 1 篇
4. Evaluating the Evaluation of Music Generation Models with Generative Psychometrics
基于生成心理测量学的音乐生成模型评估方法评估
AI 总结:该研究梳理2020-2025年ISMIR音乐生成论文的主观评估方法,用生成心理测量学分析284个标准化评估项,得出6个稳定质量维度,为音乐生成模型评估提供统一方法。
链接:https://arxiv.org/abs/2611.21809
作者:João Carlos Santana Silveira, Caio Von Rondow Morais, Frederico Pedrosa, Lucas N. Ferreira
英文摘要:Subjective user studies are one of the major methods for evaluating music generation models. However, subjective evaluation protocols vary widely and are rarely specified in enough detail to be reproduced, hindering comparison across studies. In this paper, we map subjective evaluation methods in ISMIR music generation papers from 2020-2025 and apply generative psychometrics to assess the stability of their items. We extract 284 items from the papers' methodological descriptions, using an LLM and manual validation to standardize them. We represent these items as contextual embeddings and apply Unique Variable Analysis to remove redundant, locally dependent items and Bootstrap Exploratory Graph Analysis to estimate their latent dimensions. Results show the network converges onto a taxonomy of six stable quality dimensions: Rhythm, Melody, Audio, Composition, Structure, and Lyrics, pointing to a unified methodology for conducting user studies to evaluate music generation models.
