# Semantic enrichment towards efficient speech representations

arXiv: https://arxiv.org/abs/2307.01323 · HTML: https://mlsanity.com/paper/2307.01323/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 29 references that are in the map.
- First posted on arXiv 3 Jul 2023.

## Builds on (most cited first, 20 of 20)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [Language-agnostic BERT Sentence Embedding](https://mlsanity.com/paper/2007.01852/) (2020)
- [XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale](https://mlsanity.com/paper/2111.09296/) (2021)
- [Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders](https://mlsanity.com/paper/1910.12638/) (2019)
- [TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech](https://mlsanity.com/paper/2007.06028/) (2020)
- [Emotion Recognition from Speech Using Wav2vec 2.0 Embeddings](https://mlsanity.com/paper/2104.03502/) (2021)
- [Towards end-to-end spoken language understanding](https://mlsanity.com/paper/1802.08395/) (2018)
- [Large-scale Self-Supervised Speech Representation Learning for Automatic Speaker Verification](https://mlsanity.com/paper/2110.05777/) (2021)
- [From Audio to Semantics: Approaches to end-to-end spoken language understanding](https://mlsanity.com/paper/1809.09190/) (2018)
- [Leveraging Unpaired Text Data for Training End-to-End Speech-to-Intent Systems](https://mlsanity.com/paper/2010.04284/) (2020)
- [SAMU-XLSR: Semantically-Aligned Multimodal Utterance-level Cross-Lingual Speech Representation](https://mlsanity.com/paper/2205.08180/) (2022)
- [Curriculum-based transfer learning for an effective end-to-end spoken language understanding and domain portability](https://mlsanity.com/paper/1906.07601/) (2019)
- [Why does Self-Supervised Learning for Speech Recognition Benefit Speaker Recognition?](https://mlsanity.com/paper/2204.12765/) (2022)
- [Using Speech Synthesis to Train End-to-End Spoken Language Understanding Models](https://mlsanity.com/paper/1910.09463/) (2019)
- [Tie Your Embeddings Down: Cross-Modal Latent Spaces for End-to-end Spoken Language Understanding](https://mlsanity.com/paper/2011.09044/) (2020)
- [On the use of Self-supervised Pre-trained Acoustic and Linguistic Features for Continuous Speech Emotion Recognition](https://mlsanity.com/paper/2011.09212/) (2020)
- [On the Use of Semantically-Aligned Speech Representations for Spoken Language Understanding](https://mlsanity.com/paper/2210.05291/) (2022)

## Built on by (most cited first, 2 of 2)

- [New Semantic Task for the French Spoken Language Understanding MEDIA Benchmark](https://mlsanity.com/paper/2403.19727/) (2024)
- [A dual task learning approach to fine-tune a multilingual semantic speech encoder for Spoken Language Understanding](https://mlsanity.com/paper/2406.12141/) (2024)

## Abstract (arXiv)

Over the past few years, self-supervised learned speech representations have emerged as fruitful replacements for conventional surface representations when solving Spoken Language Understanding (SLU) tasks. Simultaneously, multilingual models trained on massive textual data were introduced to encode language agnostic semantics. Recently, the SAMU-XLSR approach introduced a way to make profit from such textual models to enrich multilingual speech representations with language agnostic semantics. By aiming for better semantic extraction on a challenging Spoken Language Understanding task and in consideration with computation costs, this study investigates a specific in-domain semantic enrichment of the SAMU-XLSR model by specializing it on a small amount of transcribed data from the downstream task. In addition, we show the benefits of the use of same-domain French and Italian benchmarks for low-resource language portability and explore cross-domain capacities of the enriched SAMU-XLSR.