While everyone focuses on latency, there are many measurable aspects of ASR that are easy to evaluate and have a significant impact on user experience. Here are some of them:...

While end-to-end speech recognition systems are dominating leaderboards, it's still valuable to consider the separate acoustic and language models. This separation present in the network as the lower layers of...

The recent release of the FAIR omnilingual model, LeCun news and active use of wav2vec in "semantics" made me think again about SSL in speech. This is going to be...

Обновлено 14.09.2025 * Добавлена модель Vikhr Borealis Обновлено 17.08.2025: * Добавлены Nemo Canary V2 и Whisper Podlodka Turbo Обновлено 15.08.2025: * Добавлена Nemo Parakeet V3 Обновлено 21.07.2025: * Добавлены потоковые...

Generative error correction is a thing recently, there are many papers on that, even a challenge: Some notable papers: * Large language model based generative error correction: A challenge and...

Some features are somewhat small and require few lines of code, not really worth a conference paper or a poster. Still, they are somewhat widespread. A blog post about them...

Discrete units made a splash since Hubert probably (2021, four years already), then with Tortoise TTS and successors. Before that there were many attempts too, like the very old system...

Recently I've spent some time with [Matcha](https://github.com/shivammehta25/Matcha-TTS) by Shivam Mehta. Some related papers [Matcha-TTS: A fast TTS architecture with conditional flow matching](https://arxiv.org/abs/2309.03199) [Should you use a probabilistic duration model in...

We spent last year working mostly on TTS just as in the good old Festival times. Here are some more random thoughts I have on the subject. Rants follow, I...

We recently evaluated Russian open source and proprietary TTS models. Here are the results: {:class="table table-bordered"} |Engine | Voice | CER | xRT GPU | xRT CPU | UTMOS |...