11 articles tagged with #music-generation. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.
Researchers discovered a vulnerability in AI music and video generation systems where phonetic prompts can bypass copyright filters. The 'Adversarial PhoneTic Prompting' attack achieves 91% similarity to copyrighted content by using sound-alike phrases that preserve acoustic patterns while evading text-based detection.
AI music platform Suno's copyright filters can be easily bypassed with minimal effort, allowing users to generate AI imitations of popular songs from artists like Beyoncé, Black Sabbath, and Aqua. Despite Suno's policy prohibiting copyrighted material use, the platform's detection system proves inadequate at preventing copyright infringement.
Google's Gemini app has integrated Lyria 3, its most advanced music generation model, allowing users to create 30-second music tracks from text or image inputs. This feature democratizes music creation by making AI-powered composition accessible to anyone through the Gemini interface.
A new neural network called Jukebox has been introduced that can generate music and rudimentary singing as raw audio across various genres and artist styles. The developers are releasing the model weights, code, and exploration tools to the public.
OpenAI has created MuseNet, a deep neural network capable of generating 4-minute musical compositions using 10 different instruments and combining various musical styles from country to classical to rock. The system uses the same transformer technology as GPT-2, learning musical patterns through unsupervised training on hundreds of thousands of MIDI files rather than explicit musical programming.
Google has released Lyria 3 Pro, an upgraded AI music generation tool that can create tracks up to three minutes long, six times longer than the previous 30-second limit. The tool allows users to prompt for specific song elements like intros, choruses, and bridges, and can generate both music and lyrics from text prompts or reference photos.
Researchers developed SMDIM, a new diffusion model for symbolic music generation that efficiently handles long sequences by combining global structure construction with local refinement. The model outperforms existing approaches in both generation quality and computational efficiency across various musical styles including Western classical, popular, and folk music.
Researchers propose GACA-DiT, a new AI framework that generates music synchronized with dance movements using diffusion transformers. The system addresses limitations of existing methods by incorporating genre-adaptive rhythm extraction and context-aware temporal alignment for better synchronization between dance and music.
Researchers introduce Depth-Structured Music Recurrence (DSMR), a new AI training method for symbolic music generation that processes complete compositions efficiently. The technique uses stateful recurrent attention with distributed memory across layers, achieving similar performance to full-memory models while using 59% less GPU memory and 36% higher throughput.
Researchers introduce CMI-RewardBench, a comprehensive evaluation framework for music generation AI models that can process multimodal inputs including text, lyrics, and audio. The system includes a 110k sample preference dataset and reward models that show strong correlation with human judgments for music quality assessment.
Researchers introduce SyncTrack, an AI model for multi-track music generation that addresses rhythmic stability and synchronization issues in existing models. The model uses track-shared modules for common rhythm and track-specific modules for diverse timbres, introducing new metrics to evaluate multi-track music quality.
