Yandex is developing a unified neural network for speech and text. They are already looking for employees to work on multimodal SpeechGPT. This is indicated in the company’s job offers section, writes Kommersant.
Subscribe to RB.RU on Telegram
The company explained that they are working on multimodality in the Alice assistant and other services. Yandex did not answer the question about a single neural network.
Multimodal models with audio support, according to Dmitry Dyrmovsky, general director of the TsRT group of companies, are capable of “recognizing speech in various languages, separating lines of speakers, identifying emotions and complex non-verbal techniques, such as irony and sarcasm “. At the same time, they will be able to reduce the barrier to entry for speech technologies.
In March 2024, Yandex introduced the YandexGPT 3 line of neural networks. The first language model of the line, YandexGPT 3 Pro, works better with complex queries and more accurately follows the given response format.
YandexGPT is a neural network capable of creating and processing texts, taking into account the context of the conversation with the user. You can briefly retell articles from the Internet, summarize information from product reviews, create product descriptions for marketplace sellers, and write advertisements.
Author:
Karina Pardaeva
Source: RB
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
