Mixture-of-Experts (MoE) models have become popular in machine learning, boosting performance by partitioning tasks across multiple experts. However, the need for several experts often results in high computational costs, limiting their application on resource-constrained devices with stringent real-time requirements, such as cochlear implants (CIs). We introduce the Omni-Expert (OE) - a simple and efficient solution that leverages feature transformations to achieve the'divideand-conquer' functionality of a full MoE ensemble in a single expert model. We demonstrate the effectiveness of the OE using phoneme-specific time-frequency masking for speech dereverberation in a CI. Empirical results show that the OE delivers statistically significant improvements in objective intelligibility measures of CI vocoded speech at different levels of reverberation across various speech datasets at a much reduced computational cost relative to a counterpart MoE.

Casey Harrell has had a set of electrodes embedded in his brain for almost three years. Harrell, who has amyotrophic lateral sclerosis (ALS) and is paralyzed, first used his brain-computer interface (BCI) to "speak" sentences with the help of a research team in 2023. Since then, Harrell has clocked thousands of hours of use. He can use the device largely independently, once he's been "plugged in" with the help of a carer. His team has added new features to it, and Harrell also uses it to surf the web and perform his job.

The lack of publicly available high-quality and accurately labeled datasets has long been a major bottleneck for singing voice synthesis (SVS). To tackle this problem, we present M4Singer, a free-to-use Multi-style, Multi-singer Mandarin singing collection with elaborately annotated Musical scores as well as its benchmarks. Specifically, 1) we construct and release a large high-quality Chinese singing voice corpus, which is recorded by 20 professional singers, covering 700 Chinese pop songs as well as all the four SATB types (i.e., soprano, alto, tenor, and bass); 2) we take extensive efforts to manually compose the musical scores for each recorded song, which is necessary to the study of the prosody modeling for SVS. 3) To facilitate the use and demonstrate the quality of M4Singer, we conduct four different benchmark experiments: score-based SVS, controllable singing voice (CSV), singing voice conversion (SVC) and automatic music transcription (AMT). Audio samples can be found at http://m4singer.github.io.

Dubbing is a post-production process of re-recording actors' dialogues, which isextensively used infilmmaking and video production.

However, there are three challenges.

Meanwhile, deep neural networks have also achieved impressive performance in audio processing applications, both as sub-components of larger systems and as complete end-to-end systems by themselves.

Speech brain-computer interfaces (BCIs) aim to restore communication for people with paralysis by translating neural activity into text. Most systems use cascaded frameworks that decode phonemes before assembling sentences with an n-gram language model (LM), preventing joint optimization of all stages simultaneously. Here, we introduce an end-to-end Brain-to-Text (BIT) framework that translates neural activity into coherent sentences using a single differentiable neural network. Central to our approach is a cross-task, cross-species pretrained neural encoder, whose representations transfer to both attempted and imagined speech. In a cascaded setting with an n-gram LM, the pretrained encoder establishes a new state-of-the-art (SOTA) on the Brain-to-Text '24 and '25 benchmarks. Integrated end-to-end with audio large language models (LLMs) and trained with contrastive learning for cross-modal alignment, BIT reduces the word error rate (WER) of the prior end-to-end method from 24.69% to 10.22%. Notably, we find that small-scale audio LLMs markedly improve end-to-end decoding. Beyond record-setting performance, BIT aligns attempted and imagined speech embeddings to enable cross-task generalization. Altogether, our approach advances the integration of large, diverse neural datasets, paving the way for an end-to-end decoding framework that supports seamless, differentiable optimization.

Rhythmic fluctuations in acoustic energy and accompanying neuronal excitations in cortical oscillations are characteristic of human speech, yet whether a corresponding rhythmicity inheres in the articulatory movements that generate speech remains unclear. The received understanding of speech movements as discrete, goal-oriented actions struggles to make contact with the rhythmicity findings. In this work, we demonstrate that an unintuitive -- but no less principled than the conventional -- representation for discrete movements reveals a pervasive limit cycle organization and unlocks the recovery of previously inaccessible rhythmic structure underlying the motor activity of speech. These results help resolve a time-honored tension between the ubiquity of biological rhythmicity and discreteness in speech, the quintessential human higher function, by revealing a rhythmic organization at the most fundamental level of individual articulatory actions.