Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2311.14517

tinyCLAP: Distilling Constrastive Language-Audio Pretrained Models

Francesco Paissan·Elisabetta Farella
View original source ↗Read source document ↗Export metadata ↓

Abstract

Contrastive Language-Audio Pretraining (CLAP) became of crucial importance in the field of audio and speech processing. Its employment ranges from sound event detection to text-to-audio generation. However, one of the main limitations is the considerable amount of data required in the training process and the overall computational complexity during inference. This paper investigates how we can reduce the complexity of contrastive language-audio pre-trained models, yielding an efficient model that we call tinyCLAP. We derive an unimodal distillation loss from first principles and explore how the dimensionality of the shared, multimodal latent space can be reduced via pruning. TinyCLAP uses only 6% of the original Microsoft CLAP parameters with a minimal reduction (less than 5%) in zero-shot classification performance across the three sound event detection datasets on which it was tested

Explore related subjects

cs.SDcs.CLcs.LGeess.AS

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Francesco Paissan, Elisabetta Farella. 2024-09-24. tinyCLAP: Distilling Constrastive Language-Audio Pretrained Models. https://doi.org/10.21437/interspeech.2024-193

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

KEEP EXPLORING

Related papers

arXiv2026

Streaming Generation for Music Accompaniment

Music generation models can produce high-fidelity coherent accompaniment given complete audio input, but are limited to editing and loop-based workflows. We study real-time audio-to-audio accompaniment: as a model hears an input audio stream (e.g., a singer singing), it has to also simultaneously generate in real-time a coherent accompanying stream (e.g., a guitar accompaniment). In this work, we propose a model design considering inevitable system delays in practical deployment with two design variables: future visibility $t_f$, the offset between the output playback time and the latest input time used for conditioning, and output chunk duration $k$, the number of frames emitted per call. We train Transformer decoders across a grid of $(t_f,k)$ and show two consistent trade-offs: increasing effective $t_f$ improves coherence by reducing the recency gap, but requires faster inference to stay within the latency budget; increasing $k$ improves throughput but results in degraded accompaniment due to a reduced update rate. Finally, we observe that naive maximum-likelihood streaming training is insufficient for coherent accompaniment where future context is not available, motivating advanced anticipatory and agentic objectives for live jamming.

cs.SD↗
arXiv2026

M-CIF: Multi-Scale Alignment For CIF-Based Non-Autoregressive ASR

The Continuous Integrate-and-Fire (CIF) mechanism provides effective alignment for non-autoregressive (NAR) speech recognition. This mechanism creates a smooth and monotonic mapping from acoustic features to target tokens, achieving performance on Mandarin competitive with other NAR approaches. However, without finer-grained guidance, its stability degrades in some languages such as English and French. In this paper, we propose Multi-scale CIF (M-CIF), which performs multi-level alignment by integrating character and phoneme level supervision progressively distilled into subword representations, thereby enhancing robust acoustic-text alignment. Experiments show that M-CIF reduces WER compared to the Paraformer baseline, especially on CommonVoice by 4.21% in German and 3.05% in French. To further investigate these gains, we define phonetic confusion errors (PE) and space-related segmentation errors (SE) as evaluation metrics. Analysis of these metrics across different M-CIF settings reveals that the phoneme and character layers are essential for enhancing progressive CIF alignment.

cs.SD↗
arXiv2026

Decoding Order Matters in Autoregressive Speech Synthesis

Autoregressive speech synthesis often adopts a left-to-right order, yet generation order is a modelling choice. We investigate decoding order through masked diffusion framework, which progressively unmasks positions and allows arbitrary decoding orders during training and inference. By interpolating between identity and random permutations, we show that randomness in decoding order affects speech quality. We further compare fixed strategies, such as \texttt{l2r} and \texttt{r2l} with adaptive ones, such as Top-$K$, finding that fixed-order decoding, including the dominating left-to-right approach, is suboptimal, while adaptive decoding yields better performance. Finally, since masked diffusion requires discrete inputs, we quantise acoustic representations and find that even 1-bit quantisation can support reasonably high-quality speech.

cs.SD↗