4k citations
- Nvidia (United States)US7 papers
- Stanford UniversityUS7 papers
- University of TorontoCA7 papers
- University of California, MercedUS6 papers
- University of WashingtonUS5 papers
- Duke UniversityUS4 papers
- Massachusetts Institute of TechnologyUS4 papers
- University of CopenhagenDK4 papers
- Google (United States)US3 papers
- Nanyang Technological UniversitySG3 papers
- University of California, BerkeleyUS3 papers
- University of California, IrvineUS3 papers
4 papers · 1 filter
Citrinet: Closing the Gap between Non-Autoregressive and Autoregressive End-to-End Models for Automatic Speech Recognition
Somshubra Majumdar, Jagadeesh Balam, Oleksii Hrinchuk +3
We propose Citrinet - a new end-to-end convolutional Connectionist Temporal Classification (CTC) based automatic speech recognition (ASR) model. Citrinet is deep residual neural mo…
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…
Cross-Language Transfer Learning, Continuous Learning, and Domain Adaptation for End-to-End Automatic Speech Recognition
Jocelyn Huang, Oleksii Kuchaiev, Patrick O'Neill +5
In this paper, we demonstrate the efficacy of transfer learning and continuous learning for various automatic speech recognition (ASR) tasks. We start with a pre-trained English AS…
DARTS-ASR: Differentiable Architecture Search for Multilingual Speech Recognition and Adaptation
Yi-Chen Chen, Jui-Yang Hsu, Cheng-Kuang Lee +1
In previous works, only parameter weights of ASR models are optimized under fixed-topology architecture. However, the design of successful model architecture has always relied on h…