-
Interspeech 20232023Convolutional frontends are a typical choice for Transformer-based Automatic Speech Recognition (ASR) to preprocess the spectrogram, reduce its sequence length, and combine local information in time and frequency similarly. However, the width and height of an audio spectrogram denote different information, e.g., due to reverberation as well as the articulatory system, the time axis has a clear left-to-right
-
ECAI 20232023Question generation is an important task that helps to improve question answering performance and augment search interfaces with possible suggested questions. While multiple approaches have been proposed for this task, none addresses the goal of generating a diverse set of questions given the same input context. The main reason for this is the lack of multi-reference datasets for training such models. We
-
SIGDIAL 20232023Automatic Evaluation (AE) and Response Selection (RS) models assign quality scores to various candidate responses and rank them in conversational setups. Prior response ranking research compares various models’ performance on synthetically generated test sets. In this work, we investigate the performance of model-based reference-free AE and RS models on our constructed response ranking datasets that mirror
-
RecSys 20232023As spoken dialog systems like Siri, Alexa and Google Assistant become widespread, it becomes apparent that relying solely on global, one-size-fits-all models of Automatic Speech Recognition (ASR), Natural Language Understanding (NLU) and Entity Resolution (ER), is inadequate for delivering a friction-less customer experience. To address this issue, Query Reformulation (QR) has emerged as a crucial technique
-
ACM COMPASS 2023, NeurIPS 2023 Workshop on Tackling Climate Change with Machine Learning2023Consumer products contribute to more than 75% of global greenhouse gas (GHG) emissions, primarily through indirect contributions from the supply chain. Measurement of GHG emissions associated with products is a crucial step toward quantifying the impact of GHG emission abatement actions. Life cycle assessment (LCA), the scientific discipline for measuring GHG emissions, estimates the environmental impact
Related content
-
November 04, 2021Amazon's Georgiana Dinu on current challenges in machine translation.
-
October 11, 2021Take a behind-the-scenes look at the unique challenges the engineering teams faced, and how they used scientific research to drive fundamental innovation.
-
October 04, 2021University team application deadline is October 31, 2021.
-
October 04, 2021Publicly released TEACh dataset contains more than 3,000 dialogues and associated visual data from a simulated environment.
-
September 30, 2021Participating teams reported their progress at a workshop earlier this month.
-
September 28, 2021Preference teaching for Alexa, Alexa Custom Sound Event Detection, and Ring Custom Event Alerts let customers configure machine learning models.