# SCRAPS: Speech Contrastive Representations of Acoustic and Phonetic Spaces

arXiv: https://arxiv.org/abs/2307.12445 · HTML: https://mlsanity.com/paper/2307.12445/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 38 references that are in the map.
- First posted on arXiv 23 Jul 2023.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions](https://mlsanity.com/paper/1712.05884/) (2017)
- [Contrastive Learning with Hard Negative Samples](https://mlsanity.com/paper/2010.04592/) (2020)
- [AudioCLIP: Extending CLIP to Image, Text and Audio](https://mlsanity.com/paper/2106.13043/) (2021)
- [Keystroke Dynamics as Part of Lifelogging](https://mlsanity.com/paper/2010.10144/) (2020)
- [Wav2CLIP: Learning Robust Audio Representations From CLIP](https://mlsanity.com/paper/2110.11499/) (2021)
- [Simple but Effective: CLIP Embeddings for Embodied AI](https://mlsanity.com/paper/2111.09888/) (2021)
- [Recurrent Neural Network Transducer for Audio-Visual Speech Recognition](https://mlsanity.com/paper/1911.04890/) (2019)
- [The Voice Conversion Challenge 2018: Promoting Development of Parallel and Nonparallel Methods](https://mlsanity.com/paper/1804.04262/) (2018)
- [CLIP-Art: Contrastive Pre-training for Fine-Grained Art Classification](https://mlsanity.com/paper/2204.14244/) (2022)
- [Adapt-and-Adjust: Overcoming the Long-Tail Problem of Multilingual Speech Recognition](https://mlsanity.com/paper/2012.01687/) (2020)
- [Revisiting Over-Smoothness in Text to Speech](https://mlsanity.com/paper/2202.13066/) (2022)
- [SpeechCLIP: Integrating Speech with Pre-Trained Vision and Language Model](https://mlsanity.com/paper/2210.00705/) (2022)
- [Exploring the Impact of Negative Samples of Contrastive Learning: A Case Study of Sentence Embedding](https://mlsanity.com/paper/2202.13093/) (2022)
- [PoCoNet: Better Speech Enhancement with Frequency-Positional Embeddings, Semi-Supervised Conversational Data, and Biased Loss](https://mlsanity.com/paper/2008.04470/) (2020)
- [Improving noise robust automatic speech recognition with single-channel time-domain enhancement network](https://mlsanity.com/paper/2003.03998/) (2020)
- [SoundChoice: Grapheme-to-Phoneme Models with Semantic Disambiguation](https://mlsanity.com/paper/2207.13703/) (2022)
- [M-SpeechCLIP: Leveraging Large-Scale, Pre-Trained Models for Multilingual Speech to Image Retrieval](https://mlsanity.com/paper/2211.01180/) (2022)
- [Voice Filter: Few-shot text-to-speech speaker adaptation using voice conversion as a post-processing module](https://mlsanity.com/paper/2202.08164/) (2022)

## Abstract (arXiv)

Numerous examples in the literature proved that deep learning models have the ability to work well with multimodal data. Recently, CLIP has enabled deep learning systems to learn shared latent spaces between images and text descriptions, with outstanding zero- or few-shot results in downstream tasks. In this paper we explore the same idea proposed by CLIP but applied to the speech domain, where the phonetic and acoustic spaces usually coexist. We train a CLIP-based model with the aim to learn shared representations of phonetic and acoustic spaces. The results show that the proposed model is sensible to phonetic changes, with a 91% of score drops when replacing 20% of the phonemes at random, while providing substantial robustness against different kinds of noise, with a 10% performance drop when mixing the audio with 75% of Gaussian noise. We also provide empirical evidence showing that the resulting embeddings are useful for a variety of downstream applications, such as intelligibility evaluation and the ability to leverage rich pre-trained phonetic embeddings in speech generation task. Finally, we discuss potential applications with interesting implications for the speech generation and recognition fields.