Latent CLAP Loss for Better Foley Sound Synthesis

Tornike Karchkhadze; Hassan Salami Kavaki; Mohammad Rasool Izadi; Bryce Irvin; Mikolaj Kegler; Ari Hertz; Shuo Zhang; Marko Stamenovic

arXiv · 2403.12182

Latent CLAP Loss for Better Foley Sound Synthesis

Tornike Karchkhadze·Hassan Salami Kavaki·Mohammad Rasool Izadi·Bryce Irvin·Mikolaj Kegler·Ari Hertz·Shuo Zhang·Marko Stamenovic

View original source ↗Read source document ↗Export metadata ↓

Abstract

Foley sound generation, the art of creating audio for multimedia, has recently seen notable advancements through text-conditioned latent diffusion models. These systems use multimodal text-audio representation models, such as Contrastive Language-Audio Pretraining (CLAP), whose objective is to map corresponding audio and text prompts into a joint embedding space. AudioLDM, a text-to-audio model, was the winner of the DCASE2023 task 7 Foley sound synthesis challenge. The winning system fine-tuned the model for specific audio classes and applied a post-filtering method using CLAP similarity scores between output audio and input text at inference time, requiring the generation of extra samples, thus reducing data generation efficiency. We introduce a new loss term to enhance Foley sound generation in AudioLDM without post-filtering. This loss term uses a new module based on the CLAP mode-Latent CLAP encode-to align the latent diffusion output with real audio in a shared CLAP embedding space. Our experiments demonstrate that our method effectively reduces the Frechet Audio Distance (FAD) score of the generated audio and eliminates the need for post-filtering, thus enhancing generation efficiency.

Explore related subjects

eess.AS

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Tornike Karchkhadze, Hassan Salami Kavaki, Mohammad Rasool Izadi, Bryce Irvin, Mikolaj Kegler, Ari Hertz, Shuo Zhang, Marko Stamenovic. 2024-03-18. Latent CLAP Loss for Better Foley Sound Synthesis. https://arxiv.org/abs/2403.12182

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Recovering the Zipfian Distribution in Unsupervised Term Discovery

Unsupervised term discovery involves segmenting unlabelled speech into word- or syllable-like units and clustering these into a lexicon of candidate types. True lexicons follow a Zipfian distribution, yet the dominant centre-based clustering approach -- K-means -- produces a more uniform distribution due to an inductive bias toward spherical clusters. In this paper we revisit graph-based clustering as a bottom-up alternative, where segment embeddings are connected by pairwise similarity and partitioned using the Leiden algorithm. We show that graph clustering substantially outperforms centre-based approaches (K-means, GMM, BIRCH) in both word- and syllable-level lexicon discovery across three languages, producing more Zipf-like distributions. Another bottom-up approach, agglomerative clustering with average linkage, also performs well, although it is computationally less efficient and allows for less control over the resulting distribution. Our work calls into question the dominance of centre-based clustering for term discovery, and promotes graph clustering as an attractive alternative.

eess.AS↗

arXiv2026

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation

Strong speech-to-text (S2T) LLMs already provide robust speech perception and text reasoning, but adding speech-to-speech (S2S) output is challenging: fine-tuning the backbone can degrade the original S2T performance, while attaching a downstream talker reintroduces a serial text-to-speech bottleneck. We present PRIME-Speech, a frozen-backbone S2S conversion framework that trains only speech-generation modules. PRIME-Speech synchronizes a causal audio post-decoder with intermediate hidden states of the frozen backbone, so codec tokens are generated from the model's evolving reasoning trajectory rather than from completed text chunks. The post-decoder uses mixed hidden-state, text, and audio-history conditioning, and a training-time packing strategy with turn-level audio KV-cache and position reset stabilizes multi-turn spoken interaction without additional multi-turn S2S training data. Multi-token prediction further reduces the effective codec prediction rate and improves first-audio latency without modifying the reasoning path. Across speech translation, spoken QA, speech understanding, and multi-turn dialogue, PRIME-Speech preserves the S2T behavior of the frozen backbone while producing accurate, low-WER spoken responses.

eess.AS↗

arXiv2026

Brain2Speech-Net: Fast and Intelligible Brain-to-Speech Synthesis Without Text Decoding

The loss of speech limits communication for individuals with paralysis. Direct neural-to-speech synthesis is challenging due to the limited availability of neural data for training speech brain-computer interfaces. Most existing systems rely on cascaded neural-to-text-to-speech pipelines, which increase inference latency and propagate errors across stages. We present Brain2Speech-Net, a single-stage neural-to-speech generation framework without intermediate text decoding. We use a differentiable phoneme bottleneck and a deep-HMM alignment mechanism to map long neural recordings into the latent space of a text-to-speech (TTS) model, enabling high-quality speech synthesis. Brain2Speech-Net is the only system in our comparison that produces intelligible speech while generating faster than real time.

eess.AS↗