Challenge: Existing approaches to vocal separation are optimized for signal-level reconstruction, but they overlook structural disentanglement required for downstream generation tasks.
Approach: They propose a structure-aware learning framework to disentangle vocals, harmonies, and accompaniment . they combine global vocal identity conditioning with ranking-based objectives .
Outcome: The proposed framework disentangles lead vocals, harmonies, and accompaniment while enforcing role consistency across long-form audio.

Similar Papers

STARS: A Unified Framework for Singing Transcription, Alignment, and Refined Style Annotation (2025.findings-acl)

Copied to clipboard

Challenge: Existing automated singing annotation (ASA) methods tackle isolated aspects of the annotation pipeline.
Approach: They propose a framework that addresses transcription, alignment, and refined style annotations.
Outcome: The proposed framework delivers comprehensive multi-level annotations encompassing: (1) precise phoneme-audio alignment, (2) robust note transcription and temporal localization, (3) expressive vocal technique identification, and (4) global stylistic characterization including emotion and pace.
N-CORE: N-View Consistency Regularization for Disentangled Representation Learning in Nonverbal Vocalizations (2025.emnlp-main)

Copied to clipboard

Challenge: Nonverbal vocalizations are an essential component of human communication, conveying rich information without linguistic content.
Approach: They propose a backbone-agnostic framework to disentangle emotion and speaker information from nonverbal vocalizations by leveraging N views of audio samples to learn invariance to specific transformations.
Outcome: The proposed framework achieves competitive performance compared to state-of-the-art methods on the VIVAE, ReCANVo, and ReCANVO-Balanced datasets.
Versatile Framework for Song Generation with Prompt-based Control (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for song generation fail to generate vocals with prompt-based control and proper alignment.
Approach: VersBand is a multi-task song generation framework for synthesizing high-quality songs with prompt-based control.
Outcome: Experimental results show that VersBand performs better than baseline models across multiple song generation tasks.
Self-supervised Cross-modal Pretraining for Speech Emotion Recognition and Sentiment Analysis (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to multimodal speech emotion recognition and sentiment analysis have not improved results due to their relatively simple fusion mechanisms and lack of proper cross-modal pretraining.
Approach: They propose a deep-fused audio-text bi-modal transformer with carefully designed cross-modal fusion mechanism and stage-wise cross-mod pretraining scheme to facilitate cross-modulation.
Outcome: The proposed method exceeds benchmarks on public IEMOCAP emotion and CMU-MOSEI sentiment datasets by a large margin.
UniSpeaker: A Unified Approach for Multimodality-driven Speaker Generation (2025.findings-emnlp)

Copied to clipboard

Challenge: a new framework for speaker generation is proposed to enable multimodal speaker generation . multimodal cues such as visual appearance, textual descriptions, and other biometric signals are still in its early stages.
Approach: a new framework is proposed to enable multimodal speaker generation . the framework uses self-distillation to apply speaker disentanglement to speech generation a model is developed .
Outcome: The proposed framework is the first to support unified voice generation from arbitrary modality combinations.
AlignSTS: Speech-to-Singing Conversion via Cross-Modal Alignment (2023.findings-acl)

Copied to clipboard

Challenge: Existing approaches to speech-to-singing voice conversion are difficult to learn in text-free situations.
Approach: They propose an STS model which views speech variance as different modalities . it uses a novel rhythm adaptor to predict the target rhythm representation . they also use the predicted rhythm representation to re-align the content .
Outcome: The proposed model achieves superior performance in terms of objective and subjective metrics.
Listening Like Humans: Semantics-Guided Noise-Robust Multimodal Speech Recognition (2026.acl-long)

Copied to clipboard

Challenge: Severe acoustic degradation results in unreliable ASR outputs . et al., 2024b): critical concerns regarding reliability and fairness of ASR .
Approach: They propose a multimodal framework that reframes ASR as semantics-guided speech reconstruction.
Outcome: The proposed framework achieves an average reduction in WER while also attaining 98.71% BERTScore and 96.7% USE over advanced baselines.
Leveraging Unimodal Self-Supervised Learning for Multimodal Audio-Visual Speech Recognition (2022.acl-long)

Copied to clipboard

Challenge: Existing methods for audio-visual speech recognition use extra data to increase performance . a recent study shows that the use of unimodal self-supervised learning improves performance on multimodal tasks.
Approach: They propose to use unimodal self-supervised learning to train AVSR models on unlabelled unilateral data.
Outcome: The proposed model improves on lip reading sentences 2 by 30% even without an external language model.
Double Entendre: Robust Audio-Based AI-Generated Lyrics Detection via Multi-View Fusion (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods for detecting AI-generated music are weak and vulnerable to audio perturbations.
Approach: They propose a multimodal late-fusion pipeline that combines automatically transcribed sung lyrics and speech features capturing lyrics related information within the audio.
Outcome: The proposed method outperforms existing detectors while being more robust to audio perturbations.
ImmersiveTTS: Environment-Aware Text-to-Speech with Multimodal Diffusion Transformer and Domain-Specific Representation Alignment (2026.acl-long)

Copied to clipboard

Challenge: ImmersiveTTS model synthesizes intelligible speech and environmental audio from natural language descriptions.
Approach: They propose an environment-aware text-to-speech model that integrates natural speech with environmental audio . the model explicitly models cross-modal interactions through a dual-stream stage .
Outcome: Experimental results show that ImmersiveTTS achieves higher naturalness, intelligibility, and audio fidelity than existing approaches.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations