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.

Recent advances in multimodal deep learning have greatly enhanced the capability of systems for speech analysis and pronunciation assessment. Accurate pronunciation detection remains a key challenge in Arabic, particularly in the context of Quranic recitation, where subtle phonetic differences can alter meaning. Addressing this challenge, the present study proposes a transformer-based multimodal framework for Arabic phoneme mispronunciation detection that combines acoustic and textual representations to achieve higher precision and robustness. The framework integrates UniSpeech-derived acoustic embeddings with BERT-based textual embeddings extracted from Whisper transcriptions, creating a unified representation that captures both phonetic detail and linguistic context. To determine the most effective integration strategy, early, intermediate, and late fusion methods were implemented and evaluated on two datasets containing 29 Arabic phonemes, including eight hafiz sounds, articulated by 11 native speakers. Additional speech samples collected from publicly available YouTube recordings were incorporated to enhance data diversity and generalization. Model performance was assessed using standard evaluation metrics: accuracy, precision, recall, and F1-score, allowing a detailed comparison of the fusion strategies. Experimental findings show that the UniSpeech-BERT multimodal configuration provides strong results and that fusion-based transformer architectures are effective for phoneme-level mispronunciation detection. The study contributes to the development of intelligent, speaker-independent, and multimodal Computer-Aided Language Learning (CALL) systems, offering a practical step toward technology-supported Quranic pronunciation training and broader speech-based educational applications.

With the rise of Large Language Models (LLMs) and their vision-enabled counterparts (VLMs), numerous works have investigated their capabilities in tasks that fuse the modalities of vision and language. In this work, we benchmark the extent to which VLMs are able to act as highly-trained phoneticians, interpreting spectrograms and waveforms of speech. To do this, we synthesise a novel dataset containing 4k+ English words spoken in isolation alongside stylistically consistent spectrogram and waveform figures. We test the ability of VLMs to understand these representations of speech through a multiple-choice task whereby models must predict the correct phonemic or graphemic transcription of a spoken word when presented amongst 3 distractor transcriptions that have been selected based on their phonemic edit distance to the ground truth. We observe that both zero-shot and finetuned models rarely perform above chance, demonstrating the requirement for specific parametric knowledge of how to interpret such figures, rather than paired samples alone.