Audio ML Papers

Last 7 Days (February 28 - March 07, 2026)

Subcategories: All (37) | Speech Synthesis (5) | Music Synthesis (5) | Ambient Synthesis (1) | Quality Assessment (0) | Enhancement (2) | Asr (9) | Other (15)
← Previous Week | Current Week

🏆 Top Papers This Week

#1 TOP PAPER (Score: 83)
Siminfar Samakoush Galougah, Pranav Pulijala, Ramani Duraiswami · arXiv
A primary challenge in developing synthetic spatial hearing systems, particularly underwater, is accurately modeling sound scattering. Biological organisms achieve 3D spatial hearing by exploiting sound scattering off their bodies to generate location-dependent interaural level a...
#2 TOP PAPER (Score: 83)
Hashim Ali, Nithin Sai Adupa, Surya Subramani ... · ICASSP
Self-supervised learning (SSL) has transformed speech processing, with benchmarks such as SUPERB establishing fair comparisons across diverse downstream tasks. Despite it's security-critical importance, Audio deepfake detection has remained outside these efforts. In this work, we...
#3 TOP PAPER (Score: 83)
Minghui Wu, Haitao Tang, Jiahuan Fan ... · 2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), Singapore, 2025, pp. 1092-1097 · 2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)
Dysarthric speech reconstruction (DSR) typically employs a cascaded system that combines automatic speech recognition (ASR) and sentence-level text-to-speech (TTS) to convert dysarthric speech into normally-prosodied speech. However, dysarthric individuals often speak more slowly...
Thursday, March 05, 2026
Jihwan Lee, Parsa Razmara, Kevin Huang ... · arXiv
Speech production is a complex process spanning neural planning, motor control, muscle activation, and articulatory kinematics. While the acoustic speech signal is the most accessible product of the speech production act, it does not directly reveal its causal neurophysiological ...
Marvin Lavechin, Elika Bergelson, Roger Levy · arXiv
Studying early speech development at scale requires automatic tools, yet automatic phoneme recognition, especially for young children, remains largely unsolved. Building on decades of data collection, we curate TinyVox, a corpus of more than half a million phonetically transcribe...
Jielin Qiu, Zixiang Chen, Liangwei Yang ... · arXiv
We present a technical tutorial for building enterprise-grade realtime voice agents from first principles. While over 25 open-source speech-to-speech models and numerous voice agent frameworks exist, no single resource explains the complete pipeline from individual components to ...
Yen-Shan Chen, Shih-Yu Lai, Ying-Jung Tsou ... · arXiv
While existing audio watermarking techniques have achieved strong robustness against traditional digital signal processing (DSP) attacks, they remain vulnerable to neural resynthesis. This occurs because modern neural audio codecs act as semantic filters and discard the impercept...
Han Yin, Yang Xiao, Rohan Kumar Das ... · arXiv
Recent progress in audio generation has made it increasingly easy to create highly realistic environmental soundscapes, which can be misused to produce deceptive content, such as fake alarms, gunshots, and crowd sounds, raising concerns for public safety and trust. While deepfake...
Hao-Hui Xie, Ho-Lam Chung, Yi-Cheng Lin ... · arXiv
Large Audio-Language Models (LALMs) typically struggle with localized dialectal prosody due to the scarcity of specialized corpora. We present TW-Sound580K, a Taiwanese audio-text instruction dataset developed through a Verify-Generate-Critique (VGC) protocol. This pipeline lever...
Linghan Fang, Tianxin Xie, Li Liu · arXiv
Recently, Automatic Speech Recognition (ASR) systems (e.g., Whisper) have achieved remarkable accuracy improvements but remain highly sensitive to real-world unseen data (data with large distribution shifts), including noisy environments and diverse accents. To address this issue...
Akif Islam, Raufun Nahar, Md. Ekramul Hamid · IEEE Conference Paper
Recent advances in automatic speech recognition (ASR) and speech enhancement have led to a widespread assumption that improving perceptual audio quality should directly benefit recognition accuracy. In this work, we rigorously examine whether this assumption holds for modern zero...
Wednesday, March 04, 2026
Cemal Hanilçi, Md Sahidullah, Tomi Kinnunen · arXiv
Speech deepfake detection (SDD) is essential for maintaining trust in voice-driven technologies and digital media. Although recent SDD systems increasingly rely on self-supervised learning (SSL) representations that capture rich contextual information, complementary signal-driven...
Zachary Novack, Zack Zukowski, CJ Carr ... · ICASSP 2026
Generative audio requires fine-grained controllable outputs, yet most existing methods require model retraining on specific controls or inference-time controls (\textit{e.g.}, guidance) that can also be computationally demanding. By examining the bottlenecks of existing guidance-...
Fei Su, Cancan Li, Juan Liu ... · arXiv
Audio-Visual Speech Recognition (AVSR) integrates acoustic and visual information to enhance robustness in adverse acoustic conditions. Recent advances in Large Language Models (LLMs) have yielded competitive automatic speech recognition performance and shown effectiveness for AV...
Kevin Wilkinghoff, Sarthak Yadav, Zheng-Hua Tan · arXiv
Training-free anomalous sound detection (ASD) based on pre-trained audio embedding models has recently garnered significant attention, as it enables the detection of anomalous sounds using only normal reference data while offering improved robustness under domain shifts. However,...
Fabian Ritter-Gutierrez, Md Asif Jalal, Pablo Peso Parada ... · arXiv
Whispered-to-normal (W2N) speech conversion aims to reconstruct missing phonation from whispered input while preserving content and speaker identity. This task is challenging due to temporal misalignment between whisper and voiced recordings and lack of paired data. We propose Fl...
Tuesday, March 03, 2026
Szu-Wei Fu, Rong Chao, Xuesong Yang ... · arXiv
Universal Speech Enhancement (USE) aims to restore speech quality under diverse degradation conditions while preserving signal fidelity. Despite recent progress, key challenges in training target selection, the distortion--perception tradeoff, and data curation remain unresolved....
Mathuranathan Mayuravaani, W. Bastiaan Kleijn, Andrew Lensen ... · arXiv
This paper presents a simulation-based approach to own voice detection (OVD) in hearing aids using a single microphone. While OVD can significantly improve user comfort and speech intelligibility, existing solutions often rely on multiple microphones or additional sensors, increa...
Franziska Braun, Christopher Witzl, Florian Hönig ... · LREC 2026
Early and accessible detection of Alzheimer's disease (AD) remains a major challenge, as current diagnostic methods often rely on costly and invasive biomarkers. Speech and language analysis has emerged as a promising non-invasive and scalable approach to detecting cognitive impa...
Kashaf Gulzar, Korbinian Riedhammer, Elmar Nöth ... · arXiv
Speech-based detection of cognitive impairment (CI) offers a promising non-invasive approach for early diagnosis, yet performance disparities across demographic and clinical subgroups remain underexplored, raising concerns around fairness and generalizability. This study presents...
Franziska Braun, Christopher Witzl, Florian Hönig ... · LREC 2026
Early and accessible detection of Alzheimer's disease (AD) remains a major challenge, as current diagnostic methods often rely on costly and invasive biomarkers. Speech and language analysis has emerged as a promising non-invasive and scalable approach to detecting cognitive impa...
Xin Wang, Ge Wanying, Junichi Yamagishi · arXiv
Building speech deepfake detection models that are generalizable to unseen attacks remains a challenging problem. Although the field has shifted toward a pre-training and fine-tuning paradigm using speech foundation models, most approaches rely solely on supervised fine-tuning (S...
Monday, March 02, 2026
Hashim Ali, Nithin Sai Adupa, Surya Subramani ... · ICASSP
Self-supervised learning (SSL) has transformed speech processing, with benchmarks such as SUPERB establishing fair comparisons across diverse downstream tasks. Despite it's security-critical importance, Audio deepfake detection has remained outside these efforts. In this work, we...
Siminfar Samakoush Galougah, Pranav Pulijala, Ramani Duraiswami · arXiv
A primary challenge in developing synthetic spatial hearing systems, particularly underwater, is accurately modeling sound scattering. Biological organisms achieve 3D spatial hearing by exploiting sound scattering off their bodies to generate location-dependent interaural level a...
Minghui Wu, Xueling Liu, Jiahuan Fan ... · 2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), Singapore, Singapore, 2025, pp. 1104-1109 · 2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)
Dysarthric speech exhibits abnormal prosody and significant speaker variability, presenting persistent challenges for automatic speech recognition (ASR). While text-to-speech (TTS)-based data augmentation has shown potential, existing methods often fail to accurately model the pa...
Minghui Wu, Haitao Tang, Jiahuan Fan ... · 2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), Singapore, 2025, pp. 1092-1097 · 2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)
Dysarthric speech reconstruction (DSR) typically employs a cascaded system that combines automatic speech recognition (ASR) and sentence-level text-to-speech (TTS) to convert dysarthric speech into normally-prosodied speech. However, dysarthric individuals often speak more slowly...
Ya Jiang, Ruoyu Wang, Jingxuan Zhang ... · arXiv
This report details our submission to the CHiME-9 MCoRec Challenge on recognizing and clustering multiple concurrent natural conversations within indoor social settings. Unlike conventional meetings centered on a single shared topic, this scenario contains multiple parallel dialo...
Loan Do, Thanh Ngoc Nguyen, Thanh Pham ... · arXiv
We introduce VietSuperSpeech, a large-scale Vietnamese automatic speech recognition (ASR) dataset of 52,023 audio-text pairs totaling 267.39 hours, with a distinctive focus on casual conversational speech. Unlike existing Vietnamese ASR corpora that predominantly feature read spe...
Kirill Borodin, Vasiliy Kudryavtsev, Maxim Maslov ... · arXiv
We introduce LRLspoof, a large-scale multilingual synthetic-speech corpus for cross-lingual spoof detection, comprising 2,732 hours of audio generated with 24 open-source TTS systems across 66 languages, including 45 low-resource languages under our operational definition. To eva...
Lixing He, Zhouxuan Chen, Mingshuai Liu ... · arXiv
We propose TQCodec, a neural audio codec designed for high-bitrate, high-fidelity music streaming. Unlike existing neural codecs that primarily target ultra-low bitrates (<= 16kbps), TQCodec operates at 44.1 kHz and supports bitrates from 32 kbps to 128 kbps, aligning with the st...
Sunday, March 01, 2026
Pengfei Zhang, Tianxin Xie, Minghao Yang ... · arXiv
REPresentation Alignment (REPA) improves the training of generative flow models by aligning intermediate hidden states with pretrained teacher features, but its effectiveness in token-conditioned audio Flow Matching critically depends on the choice of supervised layers, which is ...
Hongrui Wang, Fan Zhang, Zhiyuan Yu ... · ICLR 2026
Multi-track music generation has garnered significant research interest due to its precise mixing and remixing capabilities. However, existing models often overlook essential attributes such as rhythmic stability and synchronization, leading to a focus on differences between trac...
Yanir Marmor, Arad Zulti, David Krongauz ... · arXiv
Speech processing systems face a fundamental challenge: the human voice changes with age, yet few datasets support rigorous longitudinal evaluation. We introduce VoxKnesset, an open-access dataset of ~2,300 hours of Hebrew parliamentary speech spanning 2009-2025, comprising 393 s...
Yanir Marmor, Arad Zulti, David Krongauz ... · arXiv
Speech processing systems face a fundamental challenge: the human voice changes with age, yet few datasets support rigorous longitudinal evaluation. We introduce VoxKnesset, an open-access dataset of ~2,300 hours of Hebrew parliamentary speech spanning 2009-2025, comprising 393 s...
Saturday, February 28, 2026
Seunghyun Oh, Malek Itani, Aseem Gauri ... · arXiv
Hearables are becoming ubiquitous, yet their sound controls remain blunt: users can either enable global noise suppression or focus on a single target sound. Real-world acoustic scenes, however, contain many simultaneous sources that users may want to adjust independently. We int...
Yinghao Ma, Haiwen Xia, Hewei Gao ... · arXiv
While music generation models have evolved to handle complex multimodal inputs mixing text, lyrics, and reference audio, evaluation mechanisms have lagged behind. In this paper, we bridge this critical gap by establishing a comprehensive ecosystem for music reward modeling under ...
Yinghao Ma, Haiwen Xia, Hewei Gao ... · arXiv
While music generation models have evolved to handle complex multimodal inputs mixing text, lyrics, and reference audio, evaluation mechanisms have lagged behind. In this paper, we bridge this critical gap by establishing a comprehensive ecosystem for music reward modeling under ...
Ruixiang Mao, Xiangnan Ma, Dan Chen ... · arXiv
Test-Time Scaling has shown notable efficacy in addressing complex problems through scaling inference compute. However, within Large Audio-Language Models (LALMs), an unintuitive phenomenon exists: post-training models for structured reasoning trajectories results in marginal or ...
Sen Zhang, Jianguo Wei, Wenhuan Lu ... · ICASSP 2026
The Transformer-based Whisper model has achieved state-of-the-art performance in Automatic Speech Recognition (ASR). However, its Multi-Head Attention (MHA) mechanism results in significant GPU memory consumption due to the linearly growing Key-Value (KV) cache usage, which is pr...
Jinhan Xu, Xing Tang, Houpeng Yang ... · arXiv
Symbolic music generation is a challenging task in multimedia generation, involving long sequences with hierarchical temporal structures, long-range dependencies, and fine-grained local details. Though recent diffusion-based models produce high quality generations, they tend to s...