Listen

By S. Moss. 2017

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Speech & Audio

Citations in the corpus

Visual Dialog (2016, background): “search and rescue missions) where the operator may be ‘situationally blind’ and operating via language [33] (Human: ‘Is there smoke in any room around you?’, AI: ‘Yes, in one room’, Human: ‘Go there and look for people’).”
Vision-and-Language Navigation: Interpreting Visually-Grounded Navigation Instructions in Real Environments (2017, background): “This is typically achieved either by assuming that the set of all navigation goals, or objects to be acted upon, has been enumerated, and that each will be identified by label [11, 43], or by operating in severely restricted or simulated environments requiring limited perception [10, 16, 19, 24, 29,”
Reward Augmented Maximum Likelihood for Neural Structured Prediction (2016, methodology): “As the sequence prediction model, we use an attention-based enco er-decoder recurrent model of [6] with three256-dimensional LSTM layers for encoding and one 256-dimensional LSTM layer for decoding.”
Speaker-Follower Models for Vision-and-Language Navigation (2018, background): “While a number of approaches [32, 33, 53] have been proposed for the various navigation benchmarks, they generally employ a single model that learns to map directly from instructions to actions from a limited corpus of annotated trajectories.”
VirtualHome: Simulating Household Activities Via Programs (2018, background): “However, most of the existing literature deals with a constrained problem, for example, they learn to translate navigational instructions into a sequence of robotic actions [24, 13, 10, 14].”
Advances in all-neural speech recognition (2016, methodology): “In contrast to this, we follow recent work [22, 18, 23, 19] whe re a neural network learns context-dependence implicitly.”
Learning from past mistakes: improving automatic speech recognition output via noisy-clean phrase context modeling (2018, background): “The system is trained end-to-end from acoustic features as input to predict the phonemes or characters [17, 18].”
Tactical Rewind: Self-Correction via Backtracking in Vision-And-Language Navigation (2019, background): “The natural language community has explored instruction following with 2D maps [17, 14] and more recently computer-rendered 3D environments [16].”
A Hierarchical Approach for Generating Descriptive Image Paragraphs (2016, methodology): “The Clockwork RNN [14] uses a related technique for audio signal generation, spoken word classification, and handwriting recognition; a similar hierarchical architecture was also used in [1] for speech recognition.”
Neural Machine Translation: A Review (2019, background): “recognition [84, 85], cross-lingual word-to-phone alignment [86], bioinformatics [87], text summarization [88], text normalization [89], grammatical error correction [90], question answering [91–93], natural language understanding and inference [62, 94–96], uncertainty detection [97], photo optical ”
Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotation (2021, background): “More recently, end-to-end deep learning has been used to condition agents on natural language instructions [37, 24, 38, 27, 39, 6, 7, 40], which are then trained under an imitation and/or reinforcement learning objective.”
Very Deep Self-Attention Networks for End-to-End Speech Recognition (2019, background): “Recently, the sequence-to-sequence (S2S) approach in automatic speech recognition (ASR) has received a considerable amount of interest, due to the ability to jointly train all components towards a common goal which reduces complexity and error propagation compared to traditional hybrid systems [1, 2”