Speech & Audio

Generative music tools are making electronic dance music easier to produce, but they are also creating a crisis of trust over who actually made a track. Some musicians are now investigating suspicious releases through sonic glitches, visual clues, and platform-specific patterns.

LibriBrain100 expands neural speech research with more than 100 hours of MEG recordings collected while 32 people listened to continuous natural speech. Its design combines unusually deep data from one participant with broader data for testing cross-subject adaptation.

Alibaba has launched CosyVoice Studio, a one-stop AI speech platform that combines transcription, synthesis, audio creation and real-time voice agents. The key shift is not only better speech input or output, but the addition of semantic understanding across the workflow.

Suno plans to add invisible watermarks to AI-generated audio and tighten download rules as pressure mounts from streaming abuse and copyright lawsuits. The move shows how AI music platforms are being pushed toward labeling, accountability, and tighter platform governance.

SwanTale aims to move speech generation beyond single-speaker text-to-speech by combining speaker design, acoustic scenes, and zero-shot voice reuse in one framework. The work targets creative workflows such as dubbing, audio drama, games, ads, podcasts, and short videos.

Fender CEO Edward “Bud” Cole’s comments about covers, songwriting and AI have resurfaced, drawing criticism from guitar players and music creators. The backlash reflects a broader anxiety over whether AI debates are flattening the value of human musicianship.

Fenix Flexin’s “Rubberz” has climbed onto the Billboard Hot 100, but its success has been shadowed by questions about whether the track was made with generative AI. The doubts come from more than a stylistic pivot: listeners point to audio artifacts, odd lyrics, AI-flagged visuals, and unconvincing live performances.

A new paper argues that anonymizing the sound of a voice may not be enough when multiple utterances are available. Acoustic, prosodic, and linguistic cues can accumulate and make anonymized speakers easier to verify.

A new nyra labs paper argues that modern ASR systems often treat verbatim and intended transcription styles as an uncontrolled hidden variable. The proposed approach uses task tokens and cross-attention fine-tuning to make style and word-level timing more controllable.

GigaAM Multilingual targets a problem many multilingual ASR systems still fail to solve: uneven performance for long-tail languages. Its main contribution is not only scale, but also training design that keeps dominant languages from overwhelming the rest.

This paper targets one of the hardest problems in long-audio understanding: temporal grounding. The model can answer questions with explicit timestamps over inputs as long as 120 minutes. Its key idea is to interleave periodic time markers with continuous audio tokens and train with large-scale synthetic supervision.

Qwen’s technical report introduces Qwen-Music, a music generation system designed for full songs with vocal singing. Its key idea is to plan melodies with melody tokens before rendering high-fidelity stereo audio.

According to OSChina’s summary, generative AI music platform Suno suffered a leak involving internal source code and data collection materials, allegedly exposing large-scale scraping of music, lyrics, and audio data for model training.

Files obtained in a hacking incident reportedly show Suno scraping large amounts of music and lyrics from platforms including YouTube Music, Deezer, and Genius. The report sharpens the debate over whether AI music training is fair use or unauthorized extraction.

MetaPerch explores a simple but underused idea: bioacoustic models should learn not only from animal sounds, but also from the metadata attached to those recordings. The work uses signals such as location and time as auxiliary supervision for more robust species identification.

A new arXiv paper explores a text-free approach to second-language speech assessment using WavLM representations and dynamic time warping. The method performs strongly on phonetic scoring and offers a promising path for rhythm and intonation evaluation.