AudioCC Lab

ReviewPaperAwardTeam

Sound 2025! A Review of AudioCC Lab's Annual Highlights

The article reviews the remarkable achievements of Shanghai Jiao Tong University's Audio Cognition and Computational Acoustics Lab in 2025, covering research innovation, talent cultivation, and academic exchanges, including paper publications, model releases, team-building activities, and awards.

Jan 31, 2026 · Shanghai

AwardASRSESV

Good News | Professor Qian Yanmin Wins the Second Shanghai Jiao Tong University Ruiyuan Youth Science and Technology Award

Professor Qian Yanmin was awarded the Second Ruiyuan Youth Science and Technology Award in Information and Space Technology for his outstanding achievements in the field of auditory artificial intelligence. His innovative research effectively addressed the long-standing 'cocktail party problem' in the field, laying a technical foundation for the large-scale application of auditory processing and speech interaction technologies.

Nov 28, 2025 · Student Center, Minhang Campus, Shanghai Jiao Tong University

ChallengeSEDSSLLM

Good News | Two Championships and One Third Place in DCASE 2024 International Challenge

Shanghai Jiao Tong University, in collaboration with several universities and companies, won two championships in the Low-Complexity Acoustic Scene Classification and Industrial Machine Anomalous Sound Detection tasks, and a third place in the Automated Audio Captioning task at the DCASE 2024 International Challenge.

Jul 4, 2024

[Tutorial-28] Audio Watermarking in the Era of Generative Speech: Can It Support Traceability, Anti-Cloning, and Compliance?

This article explores audio watermarking technology in the era of generative speech, analyzing its potential applications in traceability, anti-cloning, and compliance. It details the components of watermarking systems, deployment methods, challenges, and threat models, along with evaluation criteria and key findings. Finally, it identifies core shortcomings and improvement directions for watermarking technology deployment.

Mar 23, 2026

TutorialLLMDiffusion

[Tutorial-26] Gated Attention, Linear Attention, and Diffusion Language Models

This article provides an in-depth analysis of three innovative technologies: gated attention, linear attention, and diffusion language models, exploring their design motivations, implementation paths, and development trends. Starting from the driving forces behind architectural innovation, it details the core principles, engineering practices, and application value of each technology in large models, and looks forward to future technological integration and challenges.

Mar 3, 2026

HolidayAwardTeam

Welcoming the New Spring, Galloping into a New Journey | 2026 Year of the Horse New Year Greetings from the Shanghai Jiao Tong University Auditory Cognition and Computational Acoustics Laboratory

The Shanghai Jiao Tong University Auditory Cognition and Computational Acoustics Laboratory released its 2026 Year of the Horse New Year greetings, reviewing the fruitful achievements in research, talent cultivation, international exchanges, technology transfer, and team building over the past year, and outlining the vision for the new year.

Feb 16, 2026Shanghai

TTSMultiSSL

[Tutorial-25] Sound Can Also Be Directed: Exploration and Future of Controllable Speech Generation Technology

This article introduces the latest advancements in controllable speech generation technology, covering classic model architectures like PromptTTS, Salle, and CosyVoice, as well as cutting-edge research on fine-grained instruction control and multimodal speech generation. It also discusses challenges and solutions in data generation and annotation, and outlines future research directions.

Feb 9, 2026

TutorialSTTTS

[Tutorial-22] Exploring Cutting-edge Speech Translation Technologies: Unbounded Streaming Input, Para-linguistic Transfer, and All-in-One End-to-End Models

This article delves into the latest research trends in speech translation, focusing on unbounded speech input processing in streaming translation, para-linguistic information transfer in speech-to-speech translation, and the rise of all-in-one end-to-end models. It analyzes current technological challenges and solutions, and looks ahead to future development directions.

Jan 21, 2026

TutorialTTSLLM

[Tutorial-21] Introduction of Discrete Representation: Reviewing the Development of TTS Tasks Entering the Era of Large Models

This article reviews the development of speech generation (TTS) tasks from traditional architectures to the era of large speech models, focusing on the key technologies of discrete speech representation and their impact on TTS tasks.

Jan 6, 2026

Activities

Sound 2025! A Review of AudioCC Lab's Annual Highlights

Good News | Professor Qian Yanmin Wins the Second Shanghai Jiao Tong University Ruiyuan Youth Science and Technology Award

Good News | Two Championships and One Third Place in DCASE 2024 International Challenge

[Tutorial-28] Audio Watermarking in the Era of Generative Speech: Can It Support Traceability, Anti-Cloning, and Compliance?

[Tutorial-26] Gated Attention, Linear Attention, and Diffusion Language Models

Welcoming the New Spring, Galloping into a New Journey | 2026 Year of the Horse New Year Greetings from the Shanghai Jiao Tong University Auditory Cognition and Computational Acoustics Laboratory

[Tutorial-25] Sound Can Also Be Directed: Exploration and Future of Controllable Speech Generation Technology

[Tutorial-22] Exploring Cutting-edge Speech Translation Technologies: Unbounded Streaming Input, Para-linguistic Transfer, and All-in-One End-to-End Models

[Tutorial-21] Introduction of Discrete Representation: Reviewing the Development of TTS Tasks Entering the Era of Large Models

Edit

Sound 2025! A Review of AudioCC Lab's Annual Highlights

Good News | Professor Qian Yanmin Wins the Second Shanghai Jiao Tong University Ruiyuan Youth Science and Technology Award

Good News | Two Championships and One Third Place in DCASE 2024 International Challenge

[Tutorial-28] Audio Watermarking in the Era of Generative Speech: Can It Support Traceability, Anti-Cloning, and Compliance?

[Tutorial-26] Gated Attention, Linear Attention, and Diffusion Language Models

Welcoming the New Spring, Galloping into a New Journey | 2026 Year of the Horse New Year Greetings from the Shanghai Jiao Tong University Auditory Cognition and Computational Acoustics Laboratory

[Tutorial-25] Sound Can Also Be Directed: Exploration and Future of Controllable Speech Generation Technology

[Tutorial-22] Exploring Cutting-edge Speech Translation Technologies: Unbounded Streaming Input, Para-linguistic Transfer, and All-in-One End-to-End Models

[Tutorial-21] Introduction of Discrete Representation: Reviewing the Development of TTS Tasks Entering the Era of Large Models