Related papers: k2SSL: A Faster and Better Framework for Self-Supe…

Self-supervised learning (SSL) underpins modern audio deepfake detection, yet most prior work centers on a single large wav2vec2-XLSR backbone, leaving compact under studied. We present RAPTOR, Representation Aware Pairwise-gated…

Transformer-based speech self-supervised learning (SSL) models, such as HuBERT, show surprising performance in various speech processing tasks. However, huge number of parameters in speech SSL models necessitate the compression to a more…

Recently, fine-tuning large pre-trained Transformer models using downstream datasets has received a rising interest. Despite their success, it is still challenging to disentangle the benefits of large-scale datasets and Transformer…

Self-supervised learning (SSL) methods which learn representations of data without explicit supervision have gained popularity in speech-processing tasks, particularly for single-talker applications. However, these models often have…

The ubiquity of microphone-enabled devices has lead to large amounts of unlabelled audio data being produced at the edge. The integration of self-supervised learning (SSL) and federated learning (FL) into one coherent system can potentially…

Self-supervised learning (SSL) has greatly advanced speech representation learning, but multilingual SSL models remain constrained to languages encountered during pretraining. Retraining from scratch to incorporate new languages is…

Recently, self-supervised learning (SSL) has demonstrated strong performance in speaker recognition, even if the pre-training objective is designed for speech recognition. In this paper, we study which factor leads to the success of…

In Self-Supervised Learning (SSL), pre-training and evaluation are resource intensive. In the speech domain, current indicators of the quality of SSL models during pre-training, such as the loss, do not correlate well with downstream…

Self-supervised models have had great success in learning speech representations that can generalize to various downstream tasks. However, most self-supervised models require a large amount of compute and multiple GPUs to train,…

Recent studies demonstrate the effectiveness of Self Supervised Learning (SSL) speech representations for Speech Inversion (SI). However, applying SI in real-world scenarios remains challenging due to the pervasive presence of background…

Automatic speech recognition (ASR) has shown rapid advances in recent years but still degrades significantly in far-field and noisy environments. The recent development of self-supervised learning (SSL) technology can improve the ASR…

Recently, self-supervised learning (SSL) from unlabelled speech data has gained increased attention in the automatic speech recognition (ASR) community. Typical SSL methods include autoregressive predictive coding (APC), Wav2vec2.0, and…

In this paper, we provide a new perspective on self-supervised speech models from how the training targets are obtained. We generalize the targets extractor into Offline Targets Extractor (Off-TE) and Online Targets Extractor (On-TE). Based…

Self-supervised learning (SSL) has proven vital for advancing research in natural language processing (NLP) and computer vision (CV). The paradigm pretrains a shared model on large volumes of unlabeled data and achieves state-of-the-art…

Despite recent advancements in deep learning technologies, Child Speech Recognition remains a challenging task. Current Automatic Speech Recognition (ASR) models require substantial amounts of annotated data for training, which is scarce.…

Self-Supervised Learning (SSL) models have been successfully applied in various deep learning-based speech tasks, particularly those with a limited amount of data. However, the quality of SSL representations depends highly on the…

Self-supervised speech representation learning (S3RL) is revolutionizing the way we leverage the ever-growing availability of data. While S3RL related studies typically use large models, we employ light-weight networks to comply with tight…

Large scale machine learning (ML) systems such as the Alexa automatic speech recognition (ASR) system continue to improve with increasing amounts of manually transcribed training data. Instead of scaling manual transcription to impractical…

Enhancing explainability in speech self-supervised learning (SSL) is important for developing reliable SSL-based speech processing systems. This study probes how speech SSL models encode speaker-specific information via a large-scale…

We present results from Alexa speech teams on semi-supervised learning (SSL) of acoustic models (AM) with experiments spanning over 3000 hours of GPU time, making our study one of the largest of its kind. We discuss SSL for AMs in a small…