Hari Krishna Vydana

Hari Krishna Vydana

Auto-generated profile, based on publicly available information

Hari Krishna Vydana

Faculty of Information Technology, Speech@FIT, Brno University of Technology, Brno-sted, Czech Republic

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 July 2022 in IEEE Signal Processing Letters
Verified
Journal Article
Closed access
EEEkaterina Egorova
Ekaterina Egorova
HVHari Krishna Vydana
Hari Krishna Vydana
LBLukas Burget
Lukas Burget
HCHonza Cernocky
Honza Cernocky
We propose a new end-to-end architecture for automatic speech recognition that expands the “listen, attend and spell” (LAS) paradigm. While the main word-predicting network is trained to predict words, the secondary, speller network, is optimized to predict word spellings from inner representations of the main network (e.g. word embeddings or context vectors from the attention module). We show that this joint training improves the word error rate of a word-based system and enables solving additional tasks, such as out-of-vocabulary word detection and recovery. The tests are conducted on LibriSpeech dataset consisting of 1000 h of read speech.

1 November 2020 in Circuits, Systems, and Signal Processing
Verified
Journal Article
Closed access
PDF file
HVHari Krishna Vydana
Hari Krishna Vydana
AVAnil Kumar Vuppala
Anil Kumar Vuppala