activity
20192021
most citedQuartzNet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions

31 citations · 48 across the 4 of their papers we have counts for

collaborators

6 papers

eess.AS2021

Mixer-TTS: non-autoregressive, fast and compact text-to-speech model conditioned on language model embeddings

Oktai Tatanov, Stanislav Beliaev, Boris Ginsburg

This paper describes Mixer-TTS, a non-autoregressive model for mel-spectrogram generation. The model is based on the MLP-Mixer architecture adapted for speech synthesis. The basic…

eess.AS2021

TalkNet 2: Non-Autoregressive Depth-Wise Separable Convolutional Model for Speech Synthesis with Explicit Pitch and Duration Prediction

Stanislav Beliaev, Boris Ginsburg

We propose TalkNet, a non-autoregressive convolutional neural model for speech synthesis with explicit pitch and duration prediction. The model consists of three feed-forward convo…

eess.AS20205 cited

ConVoice: Real-Time Zero-Shot Voice Style Transfer with Convolutional Network

Yurii Rebryk, Stanislav Beliaev

We propose a neural network for zero-shot voice conversion (VC) without any parallel or transcribed data. Our approach uses pre-trained models for automatic speech recognition (ASR…

eess.AS202012 cited

TalkNet: Fully-Convolutional Non-Autoregressive Speech Synthesis Model

Stanislav Beliaev, Yurii Rebryk, Boris Ginsburg

We propose TalkNet, a convolutional non-autoregressive neural model for speech synthesis. The model consists of two feed-forward convolutional networks. The first network predicts…

eess.AS201931 cited

QuartzNet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions

Samuel Kriman, Stanislav Beliaev, Boris Ginsburg +6

We propose a new end-to-end neural acoustic model for automatic speech recognition. The model is composed of multiple blocks with residual connections between them. Each block cons…

cs.LG2019

NeMo: a toolkit for building AI applications using Neural Modules

Oleksii Kuchaiev, Jason Li, Huyen Nguyen +11

NeMo (Neural Modules) is a Python framework-agnostic toolkit for creating AI applications through re-usability, abstraction, and composition. NeMo is built around neural modules, c…