281 citations · 1.6k across the 109 of their papers we have counts for
12 papers · 1 filter
Learning Modality-Invariant Representations for Speech and Images
Kenneth Leidal, David Harwath, James Glass
In this paper, we explore the unsupervised learning of a semantic embedding space for co-occurring sensory inputs. Specifically, we focus on the task of learning a semantic vector…
Learning Word Embeddings from Speech
Yu-An Chung, James Glass
In this paper, we propose a novel deep neural network architecture, Sequence-to-Sequence Audio2Vec, for unsupervised learning of fixed-length vector representations of audio segmen…
Supervised and Unsupervised Transfer Learning for Question Answering
Yu-An Chung, Hung-Yi Lee, James Glass
Although transfer learning has been shown to be successful for tasks like object and speech recognition, its applicability to question answering (QA) has yet to be well-studied. In…
Spoken Language Biomarkers for Detecting Cognitive Impairment
Tuka Alhanai, Rhoda Au, James Glass
In this study we developed an automated system that evaluates speech and language features from audio recordings of neuropsychological examinations of 92 subjects in the Framingham…
Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data
Wei-Ning Hsu, Yu Zhang, James Glass
We present a factorized hierarchical variational autoencoder, which learns disentangled and interpretable representations from sequential data without supervision. Specifically, we…
Analyzing Hidden Representations in End-to-End Automatic Speech Recognition Systems
Yonatan Belinkov, James Glass
Neural models have become ubiquitous in automatic speech recognition systems. While neural networks are typically used as acoustic models in more complex systems, recent studies ha…
MIT-QCRI Arabic Dialect Identification System for the 2017 Multi-Genre Broadcast Challenge
Suwon Shon, Ahmed Ali, James Glass
In order to successfully annotate the Arabic speech con- tent found in open-domain media broadcasts, it is essential to be able to process a diverse set of Arabic dialects. For the…
Unsupervised Domain Adaptation for Robust Speech Recognition via Variational Autoencoder-Based Data Augmentation
Wei-Ning Hsu, Yu Zhang, James Glass
Domain mismatch between training and testing can lead to significant degradation in performance in many machine learning scenarios. Unfortunately, this is not a rare situation for…
Learning Latent Representations for Speech Generation and Transformation
Wei-Ning Hsu, Yu Zhang, James Glass
An ability to model a generative process and learn a latent representation for speech in an unsupervised fashion will be crucial to process vast quantities of unlabelled speech dat…
What do Neural Machine Translation Models Learn about Morphology?
Yonatan Belinkov, Nadir Durrani, Fahim Dalvi +2
Neural machine translation (MT) models obtain state-of-the-art performance while maintaining a simple, end-to-end architecture. However, little is known about what these models lea…
Adaptive Bidirectional Backpropagation: Towards Biologically Plausible Error Signal Transmission in Neural Networks
Hongyin Luo, Jie Fu, James Glass
The back-propagation (BP) algorithm has been considered the de-facto method for training deep neural networks. It back-propagates errors from the output layer to the hidden layers…
Learning Word-Like Units from Joint Audio-Visual Analysis
David Harwath, James R. Glass
Given a collection of images and spoken audio captions, we present a method for discovering word-like acoustic units in the continuous speech signal and grounding them to semantica…