Related papers: Tracking the emergence of linguistic structure in …
Several deep neural networks have recently been shown to generate activations similar to those of the brain in response to the same input. These algorithms, however, remain largely implausible: they require (1) extraordinarily large amounts…
We present our journey in training a speech language model for Wolof, an underrepresented language spoken in West Africa, and share key insights. We first emphasize the importance of collecting large-scale, spontaneous, high-quality…
Many self-supervised speech models, varying in their pre-training objective, input modality, and pre-training data, have been proposed in the last few years. Despite impressive successes on downstream tasks, we still have a limited…
Human languages have evolved to be structured through repeated language learning and use. These processes introduce biases that operate during language acquisition and shape linguistic systems toward communicative efficiency. In this paper,…
Much recent work on Spoken Language Understanding (SLU) is limited in at least one of three ways: models were trained on oracle text input and neglected ASR errors, models were trained to predict only intents without the slot values, or…
Humans learn language by interaction with their environment and listening to other humans. It should also be possible for computational models to learn language directly from speech but so far most approaches require text. We improve on…
Large language models (LLMs) can perform remarkably complex tasks, yet the fine-grained details of how these capabilities emerge during pretraining remain poorly understood. Scaling laws on validation loss tell us how much a model improves…
The emergent cross-lingual transfer seen in multilingual pretrained models has sparked significant interest in studying their behavior. However, because these analyses have focused on fully trained multilingual models, little is known about…
Human conversations can evolve in many different ways, creating challenges for automatic understanding and summarization. Goal-oriented conversations often have meaningful sub-dialogue structure, but it can be highly domain-dependent. This…
Recently, pioneer work finds that speech pre-trained models can solve full-stack speech processing tasks, because the model utilizes bottom layers to learn speaker-related information and top layers to encode content-related information.…
Self-supervised speech models have grown fast during the past few years and have proven feasible for use in various downstream tasks. Some recent work has started to look at the characteristics of these models, yet many concerns have not…
The success of large pretrained language models (LMs) such as BERT and RoBERTa has sparked interest in probing their representations, in order to unveil what types of knowledge they implicitly capture. While prior research focused on…
Standard pretrained language models operate on sequences of subword tokens without direct access to the characters that compose each token's string representation. We probe the embedding layer of pretrained language models and show that…
We explore self-supervised models that can be potentially deployed on mobile devices to learn general purpose audio representations. Specifically, we propose methods that exploit the temporal context in the spectrogram domain. One method…
Research has shown that neural models implicitly encode linguistic features, but there has been no research showing \emph{how} these encodings arise as the models are trained. We present the first study on the learning dynamics of neural…
Probing has shown that language model representations encode rich linguistic information, but it remains unclear whether they also capture cognitive signals about human processing. In this work, we probe language model representations for…
The iterated learning model simulates the transmission of language from generation to generation in order to explore how the constraints imposed by language transmission facilitate the emergence of language structure. Despite each modelled…
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…
Speech modeling methods learn one embedding for a fixed segment of speech, typically in between 10-25 ms. The information present in speech can be divided into two categories: "what is being said" (content) and "how it is expressed" (other)…
Collecting sufficient labeled data for spoken language understanding (SLU) is expensive and time-consuming. Recent studies achieved promising results by using pre-trained models in low-resource scenarios. Inspired by this, we aim to ask:…