Audio ML Papers

Week of September 06 - September 13, 2026

Subcategories: All (12) | Speech Synthesis (2) | Music Synthesis (0) | Ambient Synthesis (2) | Quality Evaluation (0) | Enhancement (1) | Asr (1) | Llm Audio (2) | Midi Generation (0) | Generative Conditioning (0) | Other (4)
← Previous Week | Current Week →

🏆 Top Papers This Week

#1 TOP PAPER (Score: 81)
Ziyang Ma, Zhikang Niu, Wenming Tu ... · Shanghai Jiao Tong University · arXiv
We introduce AuK, an open-source foundational model that unifies speech generation and editing through a common interface of natural-language instructions and audio context. To support this broad capability set, we construct approximately 3.03 billion instruction--audio instances...
#2 TOP PAPER (Score: 81)
Bin Lin, Bo Zhao, Boyang Wang ... · StepFun · arXiv
We introduce StepAudio 3 Gen, a general-purpose audio generation model that supports zero-shot text-to-speech (TTS), voice design, vocal generation, sound effects, music, vibe speech, and mixtures of multiple audio types within a unified framework. At its core, StepAudio 3 Gen is...
#3 TOP PAPER (Score: 80)
Zhongjie Duan, Shengchuan Gao, Hong Zhang ... · Alibaba Group +1 · arXiv
Text and lyrics specify broad musical characteristics and sung content but offer limited control over musical timing, melody, and reference-based style. We introduce DiffSynth-Music (https://modelscope.cn/models/DiffSynth-Studio/DiffSynth-Music), a framework that adds composable ...
Saturday, September 12, 2026
Bin Lin, Bo Zhao, Boyang Zhang ... · StepFun · arXiv
Realtime spoken interaction demands deep reasoning, prompt responses, and fluid turn-taking. We present StepAudio 3 Realtime, an audio-language foundation model organized around a continuous listen-converse-think-act loop. Deep Perception captures rich acoustic cues to interpret ...
Ruixiang Zhao, Hualei Wang, Renhe Sun ... · Ant Group +1 · arXiv
Natural interaction in digital and physical environments requires continuous perception and timely responses. Spoken dialogue relies on acoustic and linguistic cues, while video interaction also requires grounding the conversation in evolving visual context. We present Realtime-V...
Bojro Das · Cornell University · arXiv
Asked to describe what one of six speakers in a recording talks about, audio language models describe the right one on 6 to 16% of trials, below the 16.7% a guess would give. Adding a fixed bias to the attention logits of a hundred heads, under a tenth of the model's and with no ...
Friday, September 11, 2026
Bin Lin, Bo Zhao, Boyang Wang ... · StepFun · arXiv
We introduce StepAudio 3 Gen, a general-purpose audio generation model that supports zero-shot text-to-speech (TTS), voice design, vocal generation, sound effects, music, vibe speech, and mixtures of multiple audio types within a unified framework. At its core, StepAudio 3 Gen is...
Zhongjie Duan, Shengchuan Gao, Hong Zhang ... · Alibaba Group +1 · arXiv
Text and lyrics specify broad musical characteristics and sung content but offer limited control over musical timing, melody, and reference-based style. We introduce DiffSynth-Music (https://modelscope.cn/models/DiffSynth-Studio/DiffSynth-Music), a framework that adds composable ...
Chengli Feng, Zhiyue Wu, Jiahao Song ... · StepFun +3 · arXiv
We introduce StepAudio 3 Music, a large-scale, long-form music generation model that supports explicit musical planning and open-domain text-controlled generation. The StepAudio Music Tokenizer represents audio as a 50-Hz stream from a 65536-entry single codebook, using semantica...
Thursday, September 10, 2026
Luca Della Libera, Cem Subakan, ★ Mirco Ravanelli · Mila-Quebec AI Institute +2 · arXiv
Neural audio codecs are a fundamental component of modern speech generation systems. While recent codecs achieve increasingly low bitrates, reducing frame rate remains challenging, as each token must preserve more information while maintaining reconstruction quality. We present Z...
Wednesday, September 09, 2026
Yupei Li, Qiyang Sun, Mohamed Mady ... · Imperial College London +4 · AACL 2026
Large Audio Language Models (LALMs) have shown strong performance on audio reasoning benchmarks, but accuracy alone cannot distinguish true reasoning from superficial pattern matching, often overestimating reasoning ability since high scores may result from guessing rather than g...
Mingyu Zhao, Zhiyong Wu · Tsinghua University +1 · NCMMSC 2026
We present UniStream, a fully causal 48 kHz neural audio codec for streaming speech, music, and environmental sounds. At its core is Multi-Expert Residual Vector Quantization (ME-RVQ), which replaces the single shared codebook in each residual quantization layer with four expert ...
Tuesday, September 08, 2026
Ziyang Ma, Zhikang Niu, Wenming Tu ... · Shanghai Jiao Tong University · arXiv
We introduce AuK, an open-source foundational model that unifies speech generation and editing through a common interface of natural-language instructions and audio context. To support this broad capability set, we construct approximately 3.03 billion instruction--audio instances...
Bella Godiva, Yeonju Kim, Yong Man Ro · KAIST · EMNLP 2026
Full-duplex spoken dialogue systems enable simultaneous listening and speaking, but their audio-only perception often fails under background noise and overlapping speech, leading to incoherent responses. Recent audio-visual dialogue approaches show that incorporating visual cues ...
Orantqing, Shengpeng Ji, Junlong Tong ... · Tencent +4 · arXiv
In this work, we present Gander, an end-to-end model that unifies omni perception, realtime interaction, and agentic capabilities within a single framework. In contrast to turn-based conventional paradigms, Gander continuously receives streaming inputs across multiple modalities,...