PaperMetrixEvidence-aware discovery
EN
Interface language English EN العربية AR Türkçe TR
Create account
Researcher profile

Vitaly Lavrukhin

6 papers in the PaperMetrix corpus

Publications

Papers by this author

  1. Jasper: An End-to-End Convolutional Neural Acoustic Model

    2019 · arXiv (Cornell University)

    In this paper, we report state-of-the-art results on LibriSpeech among end-to-end speech recognition models without any external training data. Our model, Jasper, uses only 1D convolutions, batch normalization, ReLU, dropout, and residual connections. To improve …

  2. LibriSpeech-PC: Benchmark for Evaluation of Punctuation and Capitalization Capabilities of end-to-end ASR Models

    2023 · arXiv (Cornell University)

    Traditional automatic speech recognition (ASR) models output lower-cased words without punctuation marks, which reduces readability and necessitates a subsequent text processing model to convert ASR transcripts into a proper format. Simultaneously, the development of end-to-end …

  3. EMMeTT: Efficient Multimodal Machine Translation Training

    2025

    A rising interest in the modality extension of foundation language models warrants discussion on the most effective, and efficient, multimodal training approach. This work focuses on neural machine translation (NMT) and proposes a joint multimodal …

  4. Open Automatic Speech Recognition Models for Classical and Modern Standard Arabic

    2025 · arXiv (Cornell University)

    Despite Arabic being one of the most widely spoken languages, the development of Arabic Automatic Speech Recognition (ASR) systems faces significant challenges due to the language's complexity, and only a limited number of public Arabic …

  5. TurboBias: Universal ASR Context-Biasing powered by GPU-accelerated Phrase-Boosting Tree

    2025 · arXiv (Cornell University)

    Recognizing specific key phrases is an essential task for contextualized Automatic Speech Recognition (ASR). However, most existing context-biasing approaches have limitations associated with the necessity of additional model training, significantly slow down the decoding process, …

  6. NeMo: a toolkit for building AI applications using Neural Modules

    2019 · arXiv (Cornell University)

    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, conceptual blocks of neural networks that take typed inputs and produce typed …