Papers with subjective metrics

9 papers
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.
DiVISe: Direct Visual-Input Speech Synthesis Preserving Speaker Characteristics And Intelligibility (2025.findings-naacl)

Copied to clipboard

Challenge: Video-to-speech (V2S) synthesis requires acoustic hints to accurately reconstruct both speech content and speaker characteristics from video clips alone.
Approach: They propose a video-to-speech (V2S) model that predicts Mel-spectrograms directly from video frames.
Outcome: The proposed model outperforms existing models in acoustic intelligibility and preserves speaker-specific characteristics.
In-depth Research Impact Summarization through Fine-Grained Temporal Citation Analysis (2026.acl-long)

Copied to clipboard

Challenge: citation counts are a shallow view that fails to capture how a paper has influenced subsequent work.
Approach: They propose a task to generate nuanced, expressive, and time-aware impact summaries . they analyze fine-grained confirmatory and correction citation intents to generate summary .
Outcome: The proposed task shows moderate to strong human correlation on subjective metrics such as insightfulness.
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.
Learning the Beauty in Songs: Neural Singing Voice Beautifier (2022.acl-long)

Copied to clipboard

Challenge: Existing techniques for pitch correction are limited to intonation but ignore the overall aesthetic quality.
Approach: They propose a novel time-warping approach for pitch correction to synchronize the amateur recording with the template pitch curve.
Outcome: The proposed model improves intonation and vocal tone while keeping content and vocal timbre.
UniCoM: A Universal Code-Switching Speech Generator (2025.findings-emnlp)

Copied to clipboard

Challenge: Code-switching (CS) is a common phenomenon in real-world conversations and poses significant challenges for multilingual speech technology.
Approach: They propose a pipeline for generating high-quality, natural CS samples without altering sentence semantics.
Outcome: The proposed pipeline generates high-quality, natural CS samples without altering sentence semantics without alteration of sentence semantic.
FluentSpeech: Stutter-Oriented Automatic Speech Editing with Context-Aware Diffusion Models (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods for speech editing still suffer from over-smoothing problem and lack of robustness due to stutter.
Approach: They propose a stutter-oriented automatic speech editing model that incorporates sutter information into the hidden sequence.
Outcome: The proposed model achieves state-of-the-art performance on a speech recording dataset . it can improve fluency of stuttering speech in terms of objective and subjective metrics.
Mind Reader: Latent User Demand-Guided Content Optimization for Generative Search Engine (2026.acl-long)

Copied to clipboard

Challenge: Generative Search Engines (GSEs) have reshaped information retrieval and Generating Engine Optimization (GEO) emerges to improve the content visibility in GSEs’ responses.
Approach: They propose a method to optimize content to cover latent semantic information of GSEs by decomposing query into diverse perspectives and capturing underlying semantic information.
Outcome: The proposed method outperforms baselines and effectively improves content visibility (with up to 2.44x objective metrics and 1.23x subjective metrics on average).
Amadeus: Autoregressive Model with Bidirectional Attribute Modelling for Symbolic Music (2026.acl-long)

Copied to clipboard

Challenge: Existing symbolic music generation models represent musical notes as a sequence of attribute tokens with fixed unidirectional dependencies.
Approach: They propose a symbolic music generation framework that adopts a autoregressive and a discrete diffusion architectures for note attributes.
Outcome: The proposed framework improves state-of-the-art models across objective and subjective metrics.

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