However, there are three challenges.

The code is available here.

We show for the first time that learning powerful representations from speech audio alone followed by fine-tuning on transcribed speech can outperform the best semi-supervised methods while being conceptually simpler.

Abstract--This paper introduces SENSE (Shared Embedding for N-lingual Speech and tExt), an open-source solution inspired by the SAMU-XLSR framework and conceptually similar to Meta AI's SONAR models. These approaches rely on a teacher-student framework to align a self-supervised speech encoder with the language-agnostic continuous representations of a text encoder at the utterance level. We describe how the original SAMU-XLSR method has been updated by selecting a stronger teacher text model and a better initial speech encoder . The source code for training and using SENSE models has been integrated into the SpeechBrain toolkit, and the first SENSE model we trained has been publicly released. We report experimental results on multilingual and multimodal semantic tasks, where our SENSE model achieves highly competitive performance. Finally, this study offers new insights into how semantics are captured in such semantically aligned speech encoders. Speech foundation models based on self-supervised learning (SSL) have brought significant advances in speech processing. These models, such as wav2vec 2.0 [1], HuBERT [2], and WavLM [3], generate learned speech representations that can be applied to a wide range of downstream speech processing tasks. By training on large amounts of unlabelled speech data, SSL models have demonstrated the ability to capture crucial speech features, such as phonemes and other acoustic units [4]. This capability has led to significant progress in multiple downstream tasks, including speech recognition [1], speech translation [5], speech separation, speaker verification, speaker diarization [3], and emotion detection [6]. Different approaches have been proposed to pretrain model by aligning speech and text, like mSLAM [7], a Massively multilingual joint pre-training for speech and text.

We introduce a two-stage self-supervised framework that combines the Joint-Embedding Predictive Architecture (JEPA) with a Density Adaptive Attention Mechanism (DAAM) for learning robust speech representations. Stage 1 uses JEPA with DAAM to learn semantic audio features via masked prediction in latent space, fully decoupled from waveform reconstruction. Stage 2 leverages these representations for efficient tokenization using Finite Scalar Quantization (FSQ) and a mixed-radix packing scheme, followed by high-fidelity waveform reconstruction with a HiFi-GAN decoder. By integrating Gaussian mixture-based density-adaptive gating into the JEPA encoder, the model performs adaptive temporal feature selection and discovers hierarchical speech structure at a low frame rate of 2.5 Hz. The resulting tokens (47.5 tokens/sec) provide a reversible, highly compressed, and language-model-friendly representation that is competitive with, and often more efficient than, existing neural audio codecs.

Abstract--Recent advancements in neural audio codecs have not only enabled superior audio compression but also enhanced speech synthesis techniques. Researchers are now exploring their potential as universal acoustic feature extractors for a broader range of speech processing tasks. Building on this trend, we introduce Codec2V ec, the first speech representation learning framework that relies exclusively on discrete audio codec units. This approach offers several advantages, including improved data storage and transmission efficiency, faster training, and enhanced data privacy. We explore masked prediction with various training target derivation strategies to thoroughly understand the effectiveness of this framework. Evaluated on the SUPERB benchmark, Codec2V ec achieves competitive performance compared to continuous-input models while reducing storage requirements by up to 16.5 and training time by 2.3, showcasing its scalability and efficiency. Over the past several years, the speech processing community has rapidly adopted self-supervised learning (SSL) followed by supervised fine-tuning as a general-purpose modeling approach for tasks ranging from automatic speech recognition and emotion recognition to speaker verification [1]- [3].