An open-source benchmark for speech-to-speech models shows that current systems produce intelligible audio but diverge from human conversational behavior in latency, dialect consistency, emotional entrainment, and prosody.
Wavlm: Large-scale self-supervised pre- training for full stack speech processing
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
representative citing papers
PnP reformulates adversarial purification as learning positive-incentive noise to defend speaker verification against attacks with high efficiency and limited impact on genuine utterances.
JASTIN is an instruction-driven audio evaluation system that achieves state-of-the-art correlation with human ratings on speech, sound, music, and out-of-domain tasks without task-specific retraining.
CoMelSinger introduces a discrete token-based zero-shot SVS framework on MaskGCT with coarse-to-fine contrastive learning and an SVT module to improve melody control and reduce prosody leakage.
CFMDCTCodec combines an MDCT-based codec with a noise-prior-aware conditional flow matching enhancer for improved low-bitrate speech quality using non-adversarial training.
Sparse MERIT uses frame-wise sparse mixture-of-experts with task-specific gating on self-supervised speech features to jointly optimize enhancement and emotion recognition, reporting gains over baselines on MSP-Podcast at low SNR.
A survey that organizes audio SSL into five objective paradigms, relates their demands to architectural biases, and interprets downstream applications as tests of generalization.
citing papers explorer
-
SPEARBench: A Benchmark for Naturalness Evaluation in Streaming Speech-to-Speech Language Models
An open-source benchmark for speech-to-speech models shows that current systems produce intelligible audio but diverge from human conversational behavior in latency, dialect consistency, emotional entrainment, and prosody.
-
Positive-Incentive Noise Predictor for Adversarial Purification in Speaker Verification
PnP reformulates adversarial purification as learning positive-incentive noise to defend speaker verification against attacks with high efficiency and limited impact on genuine utterances.
-
JASTIN: Aligning LLMs for Zero-Shot Audio and Speech Evaluation via Natural Language Instructions
JASTIN is an instruction-driven audio evaluation system that achieves state-of-the-art correlation with human ratings on speech, sound, music, and out-of-domain tasks without task-specific retraining.
-
CoMelSinger: Discrete Token-Based Zero-Shot Singing Synthesis With Structured Melody Control and Guidance
CoMelSinger introduces a discrete token-based zero-shot SVS framework on MaskGCT with coarse-to-fine contrastive learning and an SVT module to improve melody control and reduce prosody leakage.
-
CFMDCTCodec: A Low-Bitrate Neural Speech Codec with Noise-Prior-aware Conditional Flow Matching for MDCT-Spectral Enhancement
CFMDCTCodec combines an MDCT-based codec with a noise-prior-aware conditional flow matching enhancer for improved low-bitrate speech quality using non-adversarial training.
-
Joint Learning using Mixture-of-Expert-Based Representation for Speech Enhancement and Robust Emotion Recognition
Sparse MERIT uses frame-wise sparse mixture-of-experts with task-specific gating on self-supervised speech features to jointly optimize enhancement and emotion recognition, reporting gains over baselines on MSP-Podcast at low SNR.
-
From Objectives to Applications: Aligning Architectural Biases in Audio Self-Supervised Learning
A survey that organizes audio SSL into five objective paradigms, relates their demands to architectural biases, and interprets downstream applications as tests of generalization.