Search Results for author:
Found 28 papers, 3 papers with code
Online Continual Learning of End-to-End Speech Recognition Models
Continual Learning, also known as Lifelong Learning, aims to continually learn from new data as it becomes available.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Branchformer: Parallel MLP-Attention Architectures to Capture Local and Global Context for Speech Recognition and Understanding
Conformer has proven to be effective in many speech processing tasks.
Learning Question-Guided Video Representation for Multi-Turn Video Question Answering
Understanding and conversing about dynamic scenes is one of the key capabilities of AI agents that navigate the environment and convey useful information to humans.
BERT-DST: Scalable End-to-End Dialogue State Tracking with Bidirectional Encoder Representations from Transformer
We focus on a specific condition, where the ontology is unknown to the state tracker, but the target slot value (except for none and dontcare), possibly unseen during training, can be found as word segment in the dialogue context.
Speaker-Targeted Audio-Visual Models for Speech Recognition in Cocktail-Party Environments
Speech recognition in cocktail-party environments remains a significant challenge for state-of-the-art speech recognition systems, as it is extremely difficult to extract an acoustic signal of an individual speaker from a background of overlapping speech with similar frequency and temporal characteristics.
Speaker Diarization With Lexical Information
This work presents a novel approach to leverage lexical information for speaker diarization.
Understanding and Improving Recurrent Networks for Human Activity Recognition by Continuous Attention
To address these issues, we propose two attention models for human activity recognition: temporal attention and sensor attention.
End-to-End Learning of Task-Oriented Dialogs
In this thesis proposal, we address the limitations of conventional pipeline design of task-oriented dialog systems and propose end-to-end learning solutions.
Adversarial Learning of Task-Oriented Neural Dialog Models
We further discuss the covariate shift problem in online adversarial dialog learning and show how we can address that with partial access to user feedback.
Semi-Supervised Convolutional Neural Networks for Human Activity Recognition
Labeled data used for training activity recognition classifiers are usually limited in terms of size and diversity.
The CAPIO 2017 Conversational Speech Recognition System
This method was applied with the CallHome training corpus and improved individual system performances by on average 6. 1% (relative) against the CallHome portion of the evaluation set with no performance loss on the Switchboard portion.
Multi-Domain Adversarial Learning for Slot Filling in Spoken Language Understanding
Model that produces such shared representations can be combined with models trained on individual domain SLU data to reduce the amount of training samples required for developing a new domain.
Customized Nonlinear Bandits for Online Response Selection in Neural Conversation Models
Moreover, we report encouraging response selection performance of the proposed neural bandit model using the Recall@k metric for a small set of online training samples.
Iterative Policy Learning in End-to-End Trainable Task-Oriented Neural Dialog Models
In this paper, we present a deep reinforcement learning (RL) framework for iterative dialog policy optimization in end-to-end task-oriented dialog systems.
An End-to-End Trainable Neural Network Model with Belief Tracking for Task-Oriented Dialog
We present a novel end-to-end trainable neural network model for task-oriented dialog systems.
Dialog Context Language Modeling with Recurrent Neural Networks
In this work, we propose contextual language models that incorporate dialog level discourse information into language modeling.
An Approach for Self-Training Audio Event Detectors Using Web Data
The audio event detectors are trained on the labeled audio and ran on the unlabeled audio downloaded from YouTube.
Joint Online Spoken Language Understanding and Language Modeling with Recurrent Neural Networks
On SLU tasks, our joint model outperforms the independent task training model by 22. 3% on intent detection error rate, with slight degradation on slot filling F1 score.
Ranked #3 on
Intent Detection
on ATIS
Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling
Attention-based encoder-decoder neural network models have recently shown promising results in machine translation and speech recognition.
Ranked #2 on
Intent Detection
on ATIS
AudioPairBank: Towards A Large-Scale Tag-Pair-Based Audio Content Analysis
One contribution is the previously unavailable documentation of the challenges and implications of collecting audio recordings with these type of labels.
City-Identification of Flickr Videos Using Semantic Acoustic Features
In particular, we present a method to compute and use semantic acoustic features to perform city-identification and the features show semantic evidence of the identification.
Environmental Noise Embeddings for Robust Speech Recognition
We propose a novel deep neural network architecture for speech recognition that explicitly employs knowledge of the background environmental noise within a deep neural network acoustic model.
Recurrent Models for Auditory Attention in Multi-Microphone Distance Speech Recognition
Integration of multiple microphone data is one of the key ways to achieve robust speech recognition in noisy environments or when the speaker is located at some distance from the input device.
Transferring Knowledge from a RNN to a DNN
The small DNN trained on the soft RNN alignments achieved a 3. 93 WER on the Wall Street Journal (WSJ) eval92 task compared to a baseline 4. 54 WER or more than 13% relative improvement.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Deep Recurrent Neural Networks for Acoustic Modelling
We present a novel deep Recurrent Neural Network (RNN) model for acoustic modelling in Automatic Speech Recognition (ASR).
Ranked #8 on
Speech Recognition
on WSJ eval92
