Research
Researching how sound is captured, processed, and understood, from speech recognition to spatial audio.
A key aspect of attending such an event in person is being able to experience the setting in its fullness — hearing the buzz of background conversations and seeing who is around. This can be…
In this issue: HyWay enables hybrid mingling; Auto-Tables transforms non-relational tables into standard relational forms; training dense retrievers to identify high-quality in-context examples for LLM; improving pronunciation assessment in CAPT.
Because headphones rank among the most popular wearables in the market, we have an exciting opportunity to expand their capabilities through integrating existing sensors with supplementary ones to enable a wide variety of experiences that…
Imagine an AI model that can seamlessly generate high-quality content across text, images, video, and audio, all at once. Such a model would more accurately capture the multimodal nature of the world and human comprehension,…
Neural codec language models for speech synthesis We introduce a language modeling approach for text-to-speech synthesis (TTS). Specifically, we train a neural codec language model (called VALL-E) using discrete codes derived from an off-the-shelf neural…
