11 citations · 16 across the 5 of their papers we have counts for
5 papers
Rethinking AI Cloud Infrastructure for Agentic Serving Systems with the Aries Experimentation Framework
Leonid Kondrashov, Hongrui Liu, JooYoung Park +14
Autonomous agents challenge conventional LLM serving by coupling repeated inference with persistent context and sandboxed tool execution. We present Aries, a full-stack experimenta…
Improvement Speaker Similarity for Zero-Shot Any-to-Any Voice Conversion of Whispered and Regular Speech
Anastasia Avdeeva, Aleksei Gusev
Zero-shot voice conversion aims to transfer the voice of a source speaker to that of a speaker unseen during training, while preserving the content information. Although various me…
Robust Speaker Recognition with Transformers Using wav2vec 2.0
Sergey Novoselov, Galina Lavrentyeva, Anastasia Avdeeva +2
Recent advances in unsupervised speech representation learning discover new approaches and provide new state-of-the-art for diverse types of speech processing tasks. This paper pre…
STC speaker recognition systems for the NIST SRE 2021
Anastasia Avdeeva, Aleksei Gusev, Igor Korsunov +9
This paper presents a description of STC Ltd. systems submitted to the NIST 2021 Speaker Recognition Evaluation for both fixed and open training conditions. These systems consists…
Deep Speaker Embeddings for Far-Field Speaker Recognition on Short Utterances
Aleksei Gusev, Vladimir Volokhov, Tseren Andzhukaev +11
Speaker recognition systems based on deep speaker embeddings have achieved significant performance in controlled conditions according to the results obtained for early NIST SRE (Sp…