We present TokenSplit, a speech separation model that acts on discrete t...
We introduce AudioPaLM, a large language model for speech understanding ...
We present SoundStorm, a model for efficient, non-autoregressive audio
g...
We introduce LMCodec, a causal neural speech codec that provides high qu...
We introduce SPEAR-TTS, a multi-speaker text-to-speech (TTS) system that...
We introduce MusicLM, a model generating high-fidelity music from text
d...
We introduce AudioLM, a framework for high-quality audio generation with...
We present a method to separate speech signals from noisy environments i...
We propose SpeechPainter, a model for filling in gaps of up to one secon...
The increasing availability of massive data sets poses a series of chall...
A crucial aspect for the successful deployment of audio-based models
"in...
Active learning is an effective technique for reducing the labeling cost...
Coresets are small data summaries that are sufficient for model training...
Recent advances in Neural Architecture Search (NAS) have produced
state-...
Adaptive importance sampling for stochastic optimization is a promising
...
Understanding the three-dimensional (3D) structure of the genome is esse...
Modern stochastic optimization methods often rely on uniform sampling wh...