数据增强 on 语音/音频论文速递 https://nanless.github.io/audio-paper-digest-blog/tags/%E6%95%B0%E6%8D%AE%E5%A2%9E%E5%BC%BA/ Recent content in 数据增强 on 语音/音频论文速递 Hugo zh-cn Wed, 29 Apr 2026 00:00:00 +0000 A Consistent Learning Depression Detection Framework Integrating Multi-View Attention https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-a-consistent-learning-depression-detection/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-a-consistent-learning-depression-detection/ 语音生物标志物 | 6.5/10 A Framework for Controlled Multi-Speaker Audio Synthesis for Robustness Evaluation of Speaker Diarisation Systems https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-a-framework-for-controlled-multi-speaker-audio/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-a-framework-for-controlled-multi-speaker-audio/ 说话人日志 | 7.5/10 A Metric Learning Approach to Heart Murmur Detection from Phonocardiogram Recordings https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-a-metric-learning-approach-to-heart-murmur/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-a-metric-learning-approach-to-heart-murmur/ 音频分类 | 7.7/10 A Unsupervised Domain Adaptation Framework For Semi-Supervised Melody Extraction Using Confidence Matrix Replace and Nearest Neighbour Supervision https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-a-unsupervised-domain-adaptation-framework-for/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-a-unsupervised-domain-adaptation-framework-for/ 音乐信息检索 | 8.0/10 Addressing Gradient Misalignment in Data-Augmented Training for Robust Speech Deepfake Detection https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-addressing-gradient-misalignment-in-data/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-addressing-gradient-misalignment-in-data/ 语音伪造检测 | 7.0/10 Advancing Semi-Supervised Child Speech Recognition with Omni-Temporal Classification under Label Noise https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-advancing-semi-supervised-child-speech/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-advancing-semi-supervised-child-speech/ 语音识别 | 7.5/10 ATOM: Adaptive Token-Level Optimal Transport Mixup for Speech Translation https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-atom-adaptive-token-level-optimal-transport-mixup/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-atom-adaptive-token-level-optimal-transport-mixup/ 语音翻译 | 8.0/10 Attentive Masked Self-Distillation for Respiratory Sound Classification https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-attentive-masked-self-distillation-for/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-attentive-masked-self-distillation-for/ 音频分类 | 7.5/10 Automatic Music Sample Identification with Multi-Track Contrastive Learning https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-automatic-music-sample-identification-with-multi/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-automatic-music-sample-identification-with-multi/ 音频检索 | 7.5/10 Auxiliary Multi-Label Training For Improving the Robustness of Audio Deepfake Detection on AI-Processed Data https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-auxiliary-multi-label-training-for-improving-the/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-auxiliary-multi-label-training-for-improving-the/ 音频深度伪造检测 | 6.5/10 Cardiobridge-DM: Bridging Cross-Cohort Heart Sound Synthesis via Rhythm-Aware Semi-Supervised Diffusion https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-cardiobridge-dm-bridging-cross-cohort-heart-sound/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-cardiobridge-dm-bridging-cross-cohort-heart-sound/ 音频生成 | 7.5/10 Content-Preserving Speech Representation Learning Via Adaptive Segment-Level Alignment https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-content-preserving-speech-representation-learning/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-content-preserving-speech-representation-learning/ 语音识别 | 7.5/10 Contrastive Timbre Representations for Musical Instrument And Synthesizer Retrieval https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-contrastive-timbre-representations-for-musical/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-contrastive-timbre-representations-for-musical/ 音频检索 | 7.5/10 CosyAccent: Duration-Controllable Accent Normalization using Source-Synthesis Training Data https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-cosyaccent-duration-controllable-accent/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-cosyaccent-duration-controllable-accent/ 语音转换 | 7.8/10 CTC-DID: CTC-Based Arabic Dialect Identification for Streaming Applications https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-ctc-did-ctc-based-arabic-dialect-identification/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-ctc-did-ctc-based-arabic-dialect-identification/ 语音识别 | 6.5/10 Diff-vs: Efficient Audio-Aware Diffusion U-Net for Vocals Separation https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-diff-vs-efficient-audio-aware-diffusion-u-net-for/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-diff-vs-efficient-audio-aware-diffusion-u-net-for/ 语音分离 | 7.5/10 Direct Simultaneous Translation Activation for Large Audio-Language Models https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-direct-simultaneous-translation-activation-for/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-direct-simultaneous-translation-activation-for/ 语音翻译 | 6.0/10 Disentangling Physiology from Fidelity: Latent-Guided Diffusion Models for Cross-Modal Cardiac Synthesis https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-disentangling-physiology-from-fidelity-latent/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-disentangling-physiology-from-fidelity-latent/ 音频生成 | 7.5/10 Dissecting Performance Degradation in Audio Source Separation under Sampling Frequency Mismatch https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-dissecting-performance-degradation-in-audio/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-dissecting-performance-degradation-in-audio/ 音乐源分离 | 7.5/10 DiTSinger: Scaling Singing Voice Synthesis with Diffusion Transformer and Implicit Alignment https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-ditsinger-scaling-singing-voice-synthesis-with/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-ditsinger-scaling-singing-voice-synthesis-with/ 歌唱语音合成 | 7.0/10 Efficient Depression Detection from Speech via Language-Independent Prompt-Driven Reprogramming https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-efficient-depression-detection-from-speech-via/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-efficient-depression-detection-from-speech-via/ 语音生物标志物 | 7.5/10 EMG-to-Speech with Fewer Channels https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-emg-to-speech-with-fewer-channels/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-emg-to-speech-with-fewer-channels/ 语音合成 | 7.5/10 Empowering Multimodal Respiratory Sound Classification with Counterfactual Adversarial Debiasing for Out-of-Distribution Robustness https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-empowering-multimodal-respiratory-sound/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-empowering-multimodal-respiratory-sound/ 音频分类 | 7.0/10 Enhancing Dialogue-Related Speech Tasks with Generated Spoken Dialogues https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-enhancing-dialogue-related-speech-tasks-with/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-enhancing-dialogue-related-speech-tasks-with/ 语音对话系统 | 6.5/10 Enhancing Noise Robustness for Neural Speech Codecs Through Resource-Efficient Progressive Quantization Perturbation Simulation https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-enhancing-noise-robustness-for-neural-speech/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-enhancing-noise-robustness-for-neural-speech/ 语音增强 | 7.5/10 Expressive Voice Conversion with Controllable Emotional Intensity https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-expressive-voice-conversion-with-controllable/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-expressive-voice-conversion-with-controllable/ 语音转换 | 7.5/10 Fake Speech Wild: Detecting Deepfake Speech on Social Media Platform https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-fake-speech-wild-detecting-deepfake-speech-on/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-fake-speech-wild-detecting-deepfake-speech-on/ 语音伪造检测 | 7.0/10 FDCNet: Frequency Domain Channel Attention and Convolution for Lipreading https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-fdcnet-frequency-domain-channel-attention-and/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-fdcnet-frequency-domain-channel-attention-and/ 视觉语音识别 | 8.5/10 Fine-Tuning Bigvgan-V2 for Robust Musical Tuning Preservation https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-fine-tuning-bigvgan-v2-for-robust-musical-tuning/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-fine-tuning-bigvgan-v2-for-robust-musical-tuning/ 音乐生成 | 7.5/10 Generating Moving 3d Soundscapes with Latent Diffusion Models https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-generating-moving-3d-soundscapes-with-latent/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-generating-moving-3d-soundscapes-with-latent/ 空间音频 | 7.5/10 Improving Audio Event Recognition with Consistency Regularization https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-improving-audio-event-recognition-with/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-improving-audio-event-recognition-with/ 音频事件检测 | 7.0/10 Improving Binaural Distance Estimation in Reverberant Rooms Through Contrastive And Multi-Task Learning https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-improving-binaural-distance-estimation-in/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-improving-binaural-distance-estimation-in/ 声源定位 | 7.0/10 In-Sync: Adaptation of Speech Aware Large Language Models for ASR with Word level timestamp predictions https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-in-sync-adaptation-of-speech-aware-large-language/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-in-sync-adaptation-of-speech-aware-large-language/ 语音识别 | 7.0/10 Learning Linearity in Audio Consistency Autoencoders via Implicit Regularization https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-learning-linearity-in-audio-consistency/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-learning-linearity-in-audio-consistency/ 音频生成 | 7.5/10 Leveraging Multiple Speech Enhancers for Non-Intrusive Intelligibility Prediction for Hearing-Impaired Listeners https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-leveraging-multiple-speech-enhancers-for-non/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-leveraging-multiple-speech-enhancers-for-non/ 模型评估 | 7.5/10 Leveraging Text-to-Speech and Voice Conversion as Data Augmentation for Alzheimer's Disease Detection from Spontaneous Speech https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-leveraging-text-to-speech-and-voice-conversion-as/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-leveraging-text-to-speech-and-voice-conversion-as/ 语音生物标志物 | 7.0/10 Lingometer: On-Device Personal Speech Word Counting System https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-lingometer-on-device-personal-speech-word/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-lingometer-on-device-personal-speech-word/ 语音活动检测 | 8.0/10 Localizing Speech Deepfakes Beyond Transitions via Segment-Aware Learning https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-localizing-speech-deepfakes-beyond-transitions/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-localizing-speech-deepfakes-beyond-transitions/ 音频深度伪造检测 | 8.0/10 LP-CFM: Perceptual Invariance-Aware Conditional Flow Matching for Speech Modeling https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-lp-cfm-perceptual-invariance-aware-conditional/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-lp-cfm-perceptual-invariance-aware-conditional/ 语音合成 | 7.0/10 Mitigating Intra-Speaker Variability in Diarization with Style-Controllable Speech Augmentation https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-mitigating-intra-speaker-variability-in/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-mitigating-intra-speaker-variability-in/ 说话人日志 | 7.0/10 Mix2Morph: Learning Sound Morphing from Noisy Mixes https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-mix2morph-learning-sound-morphing-from-noisy-mixes/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-mix2morph-learning-sound-morphing-from-noisy-mixes/ 音频生成 | 7.5/10 Multimodal Fusion-Based IPCLIP Network for Mixed Reality Surgical Assistance https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-multimodal-fusion-based-ipclip-network-for-mixed/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-multimodal-fusion-based-ipclip-network-for-mixed/ 多模态模型 | 6.5/10 On deepfake voice detection - It’s all in the presentation https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-on-deepfake-voice-detection-its-all-in-the/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-on-deepfake-voice-detection-its-all-in-the/ 音频深度伪造检测 | 8.0/10 PAC: Pronunciation-Aware Contextualized Large Language Model-Based Automatic Speech Recognition https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-pac-pronunciation-aware-contextualized-large/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-pac-pronunciation-aware-contextualized-large/ 语音识别 | 7.0/10 PC-MCL: Patient-Consistent Multi-Cycle Learning with Multi-Label Bias Correction for Respiratory Sound Classification https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-pc-mcl-patient-consistent-multi-cycle-learning/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-pc-mcl-patient-consistent-multi-cycle-learning/ 音频分类 | 7.5/10 Phoneme-Level Visual Speech Recognition via Point-Visual Fusion and Language Model Reconstruction https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-phoneme-level-visual-speech-recognition-via-point/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-phoneme-level-visual-speech-recognition-via-point/ 视觉语音识别 | 7.5/10 Proficiency-Aware Adaptation and Data Augmentation for Robust L2 ASR https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-proficiency-aware-adaptation-and-data/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-proficiency-aware-adaptation-and-data/ 语音识别 | 6.5/10 PromptSep: Generative Audio Separation Via Multimodal Prompting https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-promptsep-generative-audio-separation-via/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-promptsep-generative-audio-separation-via/ 语音分离 | 7.5/10 Quantifying Speaker Embedding Phonological Rule Interactions in Accented Speech Synthesis https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-quantifying-speaker-embedding-phonological-rule/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-quantifying-speaker-embedding-phonological-rule/ 语音合成 | 7.0/10 Refgen: Reference-Guided Synthetic Data Generation for Anomalous Sound Detection https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-refgen-reference-guided-synthetic-data-generation/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-refgen-reference-guided-synthetic-data-generation/ 音频事件检测 | 7.5/10 Robust Accent Identification via Voice Conversion and Non-Timbral Embeddings https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-robust-accent-identification-via-voice-conversion/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-robust-accent-identification-via-voice-conversion/ 语音识别 | 7.5/10 RRPO: Robust Reward Policy Optimization for LLM-Based Emotional TTS https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-rrpo-robust-reward-policy-optimization-for-llm/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-rrpo-robust-reward-policy-optimization-for-llm/ 语音合成 | 7.5/10 SA-SSL-MOS: Self-Supervised Learning MOS Prediction with Spectral Augmentation for Generalized Multi-Rate Speech Assessment https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-sa-ssl-mos-self-supervised-learning-mos/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-sa-ssl-mos-self-supervised-learning-mos/ 语音质量评估 | 7.0/10 Scaling Ambiguity: Augmenting Human Annotation in Speech Emotion Recognition with Audio-Language Models https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-scaling-ambiguity-augmenting-human-annotation-in/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-scaling-ambiguity-augmenting-human-annotation-in/ 语音情感识别 | 6.5/10 SE-DiCoW: Self-Enrolled Diarization-Conditioned Whisper https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-se-dicow-self-enrolled-diarization-conditioned/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-se-dicow-self-enrolled-diarization-conditioned/ 语音识别 | 8.5/10 Source Separation For A Cappella Music https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-source-separation-for-a-cappella-music/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-source-separation-for-a-cappella-music/ 语音分离 | 6.5/10 Style Attack Disguise: When Fonts Become a Camouflage for Adversarial Intent https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-style-attack-disguise-when-fonts-become-a/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-style-attack-disguise-when-fonts-become-a/ 对抗样本 | 7.0/10 SynParaSpeech: Automated Synthesis of Paralinguistic Datasets for Speech Generation and Understanding https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-synparaspeech-automated-synthesis-of/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-synparaspeech-automated-synthesis-of/ 语音合成 | 7.5/10 Synthesized Data Selection via Score Distribution Matching for Te Reo Māori Automatic Speech Recognition https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-synthesized-data-selection-via-score-distribution/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-synthesized-data-selection-via-score-distribution/ 语音识别 | 8.0/10 Synthetic Data Domain Adaptation for ASR via LLM-Based Text and Phonetic Respelling Augmentation https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-synthetic-data-domain-adaptation-for-asr-via-llm/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-synthetic-data-domain-adaptation-for-asr-via-llm/ 语音识别 | 8.0/10 Three Seconds is Sufficient: A Multi-Pronged Framework for Model-Based Speaker Adaptation in ASR Under Data-Scarce Conditions https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-three-seconds-is-sufficient-a-multi-pronged/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-three-seconds-is-sufficient-a-multi-pronged/ 语音识别 | 7.0/10 Timbre-Aware Audio Difference Captioning for Anomalous Machine Sounds without Paired Training Data via Synthetic Perturbations https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-timbre-aware-audio-difference-captioning-for/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-timbre-aware-audio-difference-captioning-for/ 音频分类 | 7.5/10 Tldiffgan: A Latent Diffusion-Gan Framework with Temporal Information Fusion for Anomalous Sound Detection https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-tldiffgan-a-latent-diffusion-gan-framework-with/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-tldiffgan-a-latent-diffusion-gan-framework-with/ 音频事件检测 | 7.5/10 Towards Blind Data Cleaning: A Case Study in Music Source Separation https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-towards-blind-data-cleaning-a-case-study-in-music/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-towards-blind-data-cleaning-a-case-study-in-music/ 音乐信息检索 | 7.0/10 Towards Distance-Aware Synthetic Audio Mixtures for Universal Sound Separation https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-towards-distance-aware-synthetic-audio-mixtures/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-towards-distance-aware-synthetic-audio-mixtures/ 语音分离 | 6.5/10 Towards Effective Negation Modeling in Joint Audio-Text Models for Music https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-towards-effective-negation-modeling-in-joint/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-towards-effective-negation-modeling-in-joint/ 音乐理解 | 7.5/10 Training-Free Inference-Time Scaling for Audio Source Separation https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-training-free-inference-time-scaling-for-audio/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-training-free-inference-time-scaling-for-audio/ 语音增强 | 7.5/10 UNMIXX: Untangling Highly Correlated Singing Voices Mixtures https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-unmixx-untangling-highly-correlated-singing/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-unmixx-untangling-highly-correlated-singing/ 语音分离 | 8.5/10 Vioptt: Violin Technique-Aware Transcription from Synthetic Data Augmentation https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-vioptt-violin-technique-aware-transcription-from/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-vioptt-violin-technique-aware-transcription-from/ 音乐信息检索 | 6.5/10 WAV2LEV: Predicting Levenshtein Edit Operation Sequences For Fine-Grained Estimation of Automatic Speech Recognition Error https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-wav2lev-predicting-levenshtein-edit-operation/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-wav2lev-predicting-levenshtein-edit-operation/ 语音识别 | 7.5/10 Meta-Ensemble Learning with Diverse Data Splits for Improved Respiratory Sound Classification https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-28-meta-ensemble-learning-with-diverse-data-splits/ Tue, 28 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-28-meta-ensemble-learning-with-diverse-data-splits/ 音频分类 | 8.0/10 Psychologically-Grounded Graph Modeling for Interpretable Depression Detection https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-28-psychologically-grounded-graph-modeling-for/ Tue, 28 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-28-psychologically-grounded-graph-modeling-for/ 语音情感识别 | 8.0/10 Beyond Acoustic Sparsity and Linguistic Bias: A Prompt-Free Paradigm for Mispronunciation Detection and Diagnosis https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-27-beyond-acoustic-sparsity-and-linguistic-bias-a/ Mon, 27 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-27-beyond-acoustic-sparsity-and-linguistic-bias-a/ 发音错误检测 | 8.5/10 Transformer-Based Rhythm Quantization of Performance MIDI Using Beat Annotations https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-27-transformer-based-rhythm-quantization-of/ Mon, 27 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-27-transformer-based-rhythm-quantization-of/ 音乐信息检索 | 8.0/10 Enhancing ASR Performance in the Medical Domain for Dravidian Languages https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-23-enhancing-asr-performance-in-the-medical-domain/ Thu, 23 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-23-enhancing-asr-performance-in-the-medical-domain/ 这篇论文旨在解决达罗毗荼语言（Telugu和Kannada）在医疗领域自动语音识别（ASR）中面临的标注数据稀缺和语言形态复杂两大挑战。其核心方法是提出一个“置信度感知训练框架”，该框架通过一个混合置信度评分机制（结合静态的感知、声学相似性、WER分数和动态的模型熵），对混合了真实与合成语音的训练数 Enhancing Speaker Verification with Whispered Speech via Post-Processing https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-23-enhancing-speaker-verification-with-whispered/ Thu, 23 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-23-enhancing-speaker-verification-with-whispered/ 1. **问题**：耳语语音因缺乏声带振动，其声学特征与正常语音差异显著，导致现有的说话人验证系统性能严重下降。这在用户为保护隐私而低语、或因疾病无法正常发声等实际场景中构成挑战。 2. **方法核心**：在预训练的说话人验证骨干网络（ReDimNet-B6）之上，添加一个轻量级的编码器-解码器结构 Audio Spoof Detection with GaborNet https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-22-audio-spoof-detection-with-gabornet/ Wed, 22 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-22-audio-spoof-detection-with-gabornet/ 本论文旨在解决传统SincNet前端在音频伪造检测中因有限长度sinc函数截断导致的频率泄漏问题。作者提出使用可学习的Gabor滤波器组（GaborNet）替代SincNet，并将其集成到两种先进的端到端检测架构RawNet2和RawGAT-ST中。同时，论文探索了将LEAF（Learnable F Benign Fine-Tuning Breaks Safety Alignment in Audio LLMs https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-22-benign-fine-tuning-breaks-safety-alignment-in/ Wed, 22 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-22-benign-fine-tuning-breaks-safety-alignment-in/ 这篇论文首次系统研究了良性（无害）音频数据微调对音频大模型安全对齐的破坏作用。**要解决的问题**是：用户出于提升模型性能目的进行的常规微调，是否会无意中破坏模型的安全防护？**方法**上，作者提出了一个基于嵌入空间邻近度的过滤框架，从语义、声学及混合维度，选择性地用与有害内容在表示空间上相近的良性 Environmental Sound Deepfake Detection Using Deep-Learning Framework https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-22-environmental-sound-deepfake-detection-using-deep/ Wed, 22 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-22-environmental-sound-deepfake-detection-using-deep/ 本文针对环境声音（如声音事件、声音场景）的深度伪造检测这一新兴任务，提出了一个系统的深度学习框架。**核心贡献**在于通过大量实验，系统评估了不同频谱图（MEL, CQT, Gammatone）、多种CNN架构（ResNet, Inception等）以及预训练模型（BEATs）在该任务上的表现，并验 Still Between Us? Evaluating and Improving Voice Assistant Robustness to Third-Party Interruptions https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-21-still-between-us-evaluating-and-improving-voice/ Tue, 21 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-21-still-between-us-evaluating-and-improving-voice/ 本文旨在解决语音语言模型（SLMs）在真实场景中无法有效区分主要用户与第三方插入语音（Third-Party Interruption, TPI）的问题，这会导致上下文理解失败。为此，作者首先创建了 **TPI-Train**，一个包含8.8万个样本的训练数据集，其核心设计是“说话人感知的难负例”， SpeakerRPL v2: Robust Open-set Speaker Identification through Enhanced Few-shot Foundation Tuning and Model Fusion https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-19-speakerrpl-v2-robust-open-set-speaker/ Sun, 19 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-19-speakerrpl-v2-robust-open-set-speaker/ 本文旨在解决开放集说话人识别中的鲁棒性问题，即系统在仅有少量目标说话人注册样本的情况下，需同时准确识别已知说话人并可靠拒识未知说话人。作者在先前SpeakerRPL V1框架基础上提出了三项关键改进：