Audio ML Papers

Last 7 Days (July 10 - July 17, 2026)

Subcategories: All (18) | Speech Synthesis (0) | Music Synthesis (1) | Ambient Synthesis (0) | Quality Evaluation (0) | Enhancement (0) | Asr (1) | Llm Audio (0) | Midi Generation (0) | Generative Conditioning (0) | Other (16)
← Previous Week | Current Week

🏆 Top Papers This Week

#1 TOP PAPER (Score: 81)
Jin Xu, Kangdi Wang, Ruibin Yuan ... · arXiv
In this report, we introduce Qwen-Music, a powerful music generation model capable of producing highly musical and high-fidelity songs with complete vocal singing. Qwen-Music supports two core tasks: Text to Music Generation, which create entirely new songs from text descriptions...
#2 TOP PAPER (Score: 80)
David Ayllon, Alice Baird, Jeffrey Brooks ... · arXiv
Current voice AI benchmarks typically evaluate isolated capabilities such as speech intelligibility, word error rate, or text-based dialogue quality, but they rarely test whether systems harness the acoustic information that distinguishes spoken language from its textual represen...
#3 TOP PAPER (Score: 78)
Shuai Wang, Zihan Qian, Ke Zhang ... · IEEE SLT 2026
We introduce the REAL-TSE Challenge, an IEEE SLT 2026 satellite challenge on target speaker extraction~(TSE) from real conversational recordings. Given a multi-speaker mixture and one or more enrollment utterances from a target speaker, participating systems must recover only the...
Thursday, July 16, 2026
Akın Oktav · arXiv
Machine-learnt models are increasingly used to predict ISO 3382-1 room acoustic parameters from sparse measurements, with reported coefficients of determination frequently above 0.85. This paper shows that such figures are often determined by the evaluation protocol rather than b...
Sofya Savelyeva, Mariia Perunova, Evgeny Kushnir ... · arXiv
Recent advances in text-to-speech and voice cloning make high-quality spoofing inexpensive and scalable, threatening voice authentication systems, especially automatic speaker verification (ASV). Existing defenses mainly address this threat through binary countermeasures (CMs) fo...
Wednesday, July 15, 2026
Emmanouil Karystinaios, Johannes Hentschel, Markus Neuwirth ... · ISMIR 2026
Automatic symbolic music analysis has made substantial progress, yet existing systems are typically designed for a single mode of use, such as full-score prediction, and therefore do not match the broader range of operations that arise in analysis workflows, including partial com...
Wangjin Zhou, Yizhou Zhang, Yichi Wang ... · arXiv
Supervised fine-tuning (SFT) is widely used to adapt self-supervised speech representations to downstream classification tasks. Small gains observed under a single pretrained checkpoint are often interpreted as method-level improvements, i.e., a higher attainable performance ceil...
Tuesday, July 14, 2026
Ben Maman, Frank Zalkow, Hans-Ulrich Berendes ... · International Conference on Digital Audio Effects (DAFx) 2026
Recent diffusion-based generative models have achieved strong results in domain-specific audio generation tasks such as speech, singing, and instrumental music synthesis. However, these models are typically specialized and do not generalize well to mixed or intermediate audio typ...
Monday, July 13, 2026
Yu-Han Huang, Chih-Kai Yang, Ke-Han Lu ... · arXiv
Large audio-language models (LALMs) often underperform on fine-grained, non-semantic attributes of speech, such as a speaker's emotion, despite strong performance on speech content. Improving this without the cost of retraining calls for an effective inference-time intervention, ...
Mingyue Huo, Yuheng Zhang, Hao Zhang · arXiv
Speech enhancement (SE) can substantially improve perceptual quality, yet enhanced speech does not necessarily improve automatic speech recognition (ASR). Existing remedies, such as retraining the enhancer jointly with recognizer or interpolating enhanced speech with the noisy in...
Chong Jing, Junan Zhang, Jing Yang ... · arXiv
Zero-shot instrument cloning aims to render an arbitrary [Target MIDI] sequence with the acoustic identity of an unseen instrument given only a short [Reference Audio, Reference MIDI] pair. Existing methods rely on pre-trained embeddings (e.g., CLAP) that compress the reference a...
Sunday, July 12, 2026
Stefano Bannò, Penny Karanasou, Mengjie Qian ... · arXiv
Automated assessment of second language (L2) speaking proficiency relies on large-scale annotated speech data, which remains scarce compared to widely available written learner corpora. A promising direction for addressing this imbalance is to use text-to-speech (TTS) and voice c...
Ryota Kimura, Sangheon Park, Natalia Polouliakh ... · arXiv
Dance-to-music generation is a promising task for applications such as choreography support and automatic accompaniment, where temporal coordination between body movement and sound is essential. In particular, using human joint positions as the motion representation is attractive...
Saturday, July 11, 2026
Shuhai Peng, Jinjiang Liu, Hui Lu ... · arXiv
Generative streaming models for Target Speaker Extraction (TSE) commonly exhibit a quality--intelligibility trade-off, wherein naive optimization for perceptual audio quality tends to degrade speech intelligibility, and conversely. We reveal that this trade-off arises not from th...
Fan Bu, Rongfeng Li, Linfeng Fan · arXiv
Melody skeleton extraction aims to derive a shorter melody that preserves structural notes while removing ornaments. Prior methods rely on hand-crafted reduction rules or note-wise salience classifiers trained with heuristically or procedurally generated pseudo-labels. Such super...
Kuan-Po Huang, Bo-Ru Lu, Ho-Lam Chung ... · arXiv
While recent few-step sampling text-to-audio generation models like MeanAudio substantially accelerate generation by modeling average velocities, their strict one-step generation quality still lags significantly behind multi-step counterparts. We propose FdAudio to bridge this ga...
Friday, July 10, 2026
Shikhar Bharadwaj, Kwanghee Choi, Stephen McIntosh ... · arXiv
Phone segmentation and recognition are inherently related tasks, yet modern approaches typically model them separately. We argue that phonetic structure is already latent in the representations of self-supervised speech models (S3Ms), and one only needs to steer them to solve bot...
Xugang Lu, Peng Shen, Yu Tsao ... · arXiv (preprint)
Large language model (LLM)-based audio-visual speech recognition (LLM-AVSR) has recently demonstrated strong robustness in adverse acoustic environments by leveraging complementary audio and visual information. Existing approaches typically employ independently pretrained acousti...