Speech & Audio

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.

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.

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.

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.