ParaSpeechCLAP: A Dual-Encoder Speech-Text Model for Rich Stylistic Language-Audio Pretraining

• URL: http://arxiv.org/abs/2603.28737v1
• Date: Mon, 30 Mar 2026 17:50:07 GMT
• Title: ParaSpeechCLAP: A Dual-Encoder Speech-Text Model for Rich Stylistic Language-Audio Pretraining
• Abstract summary: ParaSpeechCLAP is a dual-encoder contrastive model that maps speech and text style captions into a common embedding space.<n>We train specialized ParaSpeechCLAP-Intrinsic and ParaSpeechCLAP-Situational models alongside a unified ParaSpeechCLAP-Combined model.
• Score: 54.15873111975667
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce ParaSpeechCLAP, a dual-encoder contrastive model that maps speech and text style captions into a common embedding space, supporting a wide range of intrinsic (speaker-level) and situational (utterance-level) descriptors (such as pitch, texture and emotion) far beyond the narrow set handled by existing models. We train specialized ParaSpeechCLAP-Intrinsic and ParaSpeechCLAP-Situational models alongside a unified ParaSpeechCLAP-Combined model, finding that specialization yields stronger performance on individual style dimensions while the unified model excels on compositional evaluation. We further show that ParaSpeechCLAP-Intrinsic benefits from an additional classification loss and class-balanced training. We demonstrate our models' performance on style caption retrieval, speech attribute classification and as an inference-time reward model that improves style-prompted TTS without additional training. ParaSpeechCLAP outperforms baselines on most metrics across all three applications. Our models and code are released at https://github.com/ajd12342/paraspeechclap .

Related papers

• Audio-Visual Generalized Zero-Shot Learning using Pre-Trained Large Multi-Modal Models [53.48409081555687]
  In this work, we explore such large pre-trained models to obtain features, i.e. CLIP for visual features, and CLAP for audio features. We propose a simple yet effective model that only relies on feed-forward neural networks. Our framework achieves state-of-the-art performance on VGGSound-GZSL, UCF-GZSL, and ActivityNet-GZSL.
  arXiv  Detail & Related papers  (2024-04-09T13:39:37Z)
• Fine-tuning CLIP Text Encoders with Two-step Paraphrasing [83.3736789315201]
  We introduce a straightforward fine-tuning approach to enhance the representations of CLIP models for paraphrases. Our model, which we call ParaCLIP, exhibits significant improvements over baseline CLIP models across various tasks.
  arXiv  Detail & Related papers  (2024-02-23T06:11:50Z)
• StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models [19.029030168939354]
  StyleTTS 2 is a text-to-speech (TTS) model that leverages style diffusion and adversarial training with large speech language models (SLMs) to achieve human-level TTS synthesis. StyleTTS 2 surpasses human recordings on the single-speaker LJSpeech dataset and matches it on the multispeaker VCTK dataset as judged by native English speakers. This work achieves the first human-level TTS on both single and multispeaker datasets, showcasing the potential of style diffusion and adversarial training with large SLMs.
  arXiv  Detail & Related papers  (2023-06-13T11:04:43Z)
• A Systematic Comparison of Phonetic Aware Techniques for Speech Enhancement [20.329872147913584]
  We compare different methods of incorporating phonetic information in a speech enhancement model. We observe the influence of different phonetic content models as well as various feature-injection techniques on enhancement performance.
  arXiv  Detail & Related papers  (2022-06-22T12:00:50Z)
• GenerSpeech: Towards Style Transfer for Generalizable Out-Of-Domain Text-to-Speech Synthesis [68.42632589736881]
  This paper proposes GenerSpeech, a text-to-speech model towards high-fidelity zero-shot style transfer of OOD custom voice. GenerSpeech decomposes the speech variation into the style-agnostic and style-specific parts by introducing two components. Our evaluations on zero-shot style transfer demonstrate that GenerSpeech surpasses the state-of-the-art models in terms of audio quality and style similarity.
  arXiv  Detail & Related papers  (2022-05-15T08:16:02Z)
• GANSpeech: Adversarial Training for High-Fidelity Multi-Speaker Speech Synthesis [6.632254395574993]
  GANSpeech is a high-fidelity multi-speaker TTS model that adopts the adversarial training method to a non-autoregressive multi-speaker TTS model. In the subjective listening tests, GANSpeech significantly outperformed the baseline multi-speaker FastSpeech and FastSpeech2 models.
  arXiv  Detail & Related papers  (2021-06-29T08:15:30Z)
• Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation [63.561944239071615]
  StyleSpeech is a new TTS model which synthesizes high-quality speech and adapts to new speakers. With SALN, our model effectively synthesizes speech in the style of the target speaker even from single speech audio. We extend it to Meta-StyleSpeech by introducing two discriminators trained with style prototypes, and performing episodic training.
  arXiv  Detail & Related papers  (2021-06-06T15:34:11Z)
• Meta-Learning for Short Utterance Speaker Recognition with Imbalance Length Pairs [65.28795726837386]
  We introduce a meta-learning framework for imbalance length pairs. We train it with a support set of long utterances and a query set of short utterances of varying lengths. By combining these two learning schemes, our model outperforms existing state-of-the-art speaker verification models.
  arXiv  Detail & Related papers  (2020-04-06T17:53:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.