19 citations · 25 across the 7 of their papers we have counts for
7 papers
Optimizing Byte-level Representation for End-to-end ASR
Roger Hsiao, Liuhui Deng, Erik McDermott +2
We propose a novel approach to optimizing a byte-level representation for end-to-end automatic speech recognition (ASR). Byte-level representation is often used by large scale mult…
Personalization of CTC-based End-to-End Speech Recognition Using Pronunciation-Driven Subword Tokenization
Zhihong Lei, Ernest Pusateri, Shiyi Han +8
Recent advances in deep learning and automatic speech recognition have improved the accuracy of end-to-end speech recognition systems, but recognition of personal content such as c…
Variable Attention Masking for Configurable Transformer Transducer Speech Recognition
Pawel Swietojanski, Stefan Braun, Dogan Can +9
This work studies the use of attention masking in transformer transducer based speech recognition for building a single configurable model for different deployment scenarios. We pr…
Online Automatic Speech Recognition with Listen, Attend and Spell Model
Roger Hsiao, Dogan Can, Tim Ng +2
The Listen, Attend and Spell (LAS) model and other attention-based automatic speech recognition (ASR) models have known limitations when operated in a fully online mode. In this pa…
Generalized Multi-view Shared Subspace Learning using View Bootstrapping
Krishna Somandepalli, Shrikanth Narayanan
A key objective in multi-view learning is to model the information common to multiple parallel views of a class of objects/events to improve downstream learning tasks. In this cont…
Towards Adapting NMF Dictionaries Using Total Variability Modeling for Noise-Robust Acoustic Features
Kunal Dhawan, Colin Vaz, Ruchir Travadi +1
We propose an algorithm to extract noise-robust acoustic features from noisy speech. We use Total Variability Modeling in combination with Non-negative Matrix Factorization (NMF) t…
Multimodal Representation Learning using Deep Multiset Canonical Correlation
Krishna Somandepalli, Naveen Kumar, Ruchir Travadi +1
We propose Deep Multiset Canonical Correlation Analysis (dMCCA) as an extension to representation learning using CCA when the underlying signal is observed across multiple (more th…