Recent work has shown that it is possible to resynthesize high-quality s...
Speech language models (SpeechLMs) process and generate acoustic data on...
We present a technique for neural network verification using mixed-integ...
Word or word-fragment based Language Models (LM) are typically preferred...
In this work, we propose an algorithm for solving exact sparse linear
re...
We introduce dGSLM, the first "textless" model able to generate audio sa...
Recent work in spoken language modeling shows the possibility of learnin...
Textless spoken language processing research aims to extend the applicab...
Speech emotion conversion is the task of modifying the perceived emotion...
Speech pre-training has primarily demonstrated efficacy on classificatio...
We present the Zero Resource Speech Challenge 2021, which asks participa...
Generative spoken language modeling involves learning jointly the acoust...
We introduce a new unsupervised task, spoken language modeling: the lear...