Speech to text models tend to be trained and evaluated against a single
...
Most automatic speech processing systems are sensitive to the acoustic
e...
We present evidence that learned density functional theory (“DFT”) force...
Speech emotion conversion is the task of modifying the perceived emotion...
Popular ASR benchmarks such as Librispeech and Switchboard are limited i...
Speech pre-training has primarily demonstrated efficacy on classificatio...
We present the Zero Resource Speech Challenge 2021, which asks participa...
We introduce VoxPopuli, a large-scale multilingual corpus providing 100K...
We introduce a new unsupervised task, spoken language modeling: the lear...
Catalyst discovery and optimization is key to solving many societal and
...
Scalable and cost-effective solutions to renewable energy storage are
es...
Contrastive Predictive Coding (CPC), based on predicting future segments...
Cross-lingual and multi-lingual training of Automatic Speech Recognition...
We introduce a new collection of spoken English audio suitable for train...
The task of image generation started to receive some attention from arti...
Generative models have proven to be an outstanding tool for representing...