RNN-Transducers (RNN-Ts) have gained widespread acceptance as an end-to-...
Disfluencies commonly occur in conversational speech. Speech with
disflu...
Conversational speech often consists of deviations from the speech plan,...
In this work, we seek to build effective code-switched (CS) automatic sp...
Training state-of-the-art ASR systems such as RNN-T often has a high
ass...
Domain-specific neural machine translation (NMT) systems (e.g., in
educa...
Online alignment in machine translation refers to the task of aligning a...
We focus on the audio-visual video parsing (AVVP) problem that involves
...
RNN-Transducer (RNN-T) models have become synonymous with streaming
end-...
Post-editing in Automatic Speech Recognition (ASR) entails automatically...
We study the task of personalizing ASR models to a target non-native
spe...
While recent benchmarks have spurred a lot of new work on improving the
...
Generating code-switched text is a problem of growing interest, especial...
Automatic speech recognition (ASR) in Sanskrit is interesting, owing to ...
Recently, there is increasing interest in multilingual automatic speech
...
There have been a number of techniques that have demonstrated the genera...
Multimodal IR, spanning text corpus, knowledge graph and images, called
...
We consider the task of personalizing ASR models while being constrained...
End-to-end models for robust automatic speech recognition (ASR) have not...
Natural language processing (NLP) tasks (e.g. question-answering in Engl...
End-to-end automatic speech recognition (ASR) systems are increasingly b...
Building Automatic Speech Recognition (ASR) systems for code-switched sp...
We introduce the problem of adapting a black-box, cloud-based ASR system...
Neural language models (LMs) have shown to benefit significantly from
en...
End-to-end (E2E) models have been explored for large speech corpora and ...
Automatic question generation (QG) is a challenging problem in natural
l...
This work focuses on building language models (LMs) for code-switched te...
We analyze the performance of different sentiment classification models ...
We present CROSSGRAD, a method to use multi-domain training data to lear...
The problem of automatic accent identification is important for several
...
In this work, we present a new approach to language modeling for bilingu...
Mismatched transcriptions have been proposed as a mean to acquire
probab...