23.6k citations
- Carnegie Mellon UniversityUS49 papers
- Google (United States)US37 papers
- California Institute of TechnologyUS33 papers
- Amazon (Germany)DE32 papers
- University of Illinois Urbana-ChampaignUS22 papers
- Microsoft (United States)US20 papers
- Stanford UniversityUS20 papers
- The University of Texas at AustinUS20 papers
- University of California, Los AngelesUS20 papers
- University of California, Santa BarbaraUS19 papers
- University of WashingtonUS19 papers
- Georgia Institute of TechnologyUS17 papers
11 papers · 2 filters
Dubbing in Practice: A Large Scale Study of Human Localization With Insights for Automatic Dubbing
William Brannon, Yogesh Virkar, Brian Thompson
We investigate how humans perform the task of dubbing video content from one language into another, leveraging a novel corpus of 319.57 hours of video from 54 professionally produc…
Guided contrastive self-supervised pre-training for automatic speech recognition
Aparna Khare, Minhua Wu, Saurabhchand Bhati +2
Contrastive Predictive Coding (CPC) is a representation learning method that maximizes the mutual information between intermediate latent representations and the output of a given…
Toward Fairness in Speech Recognition: Discovery and mitigation of performance disparities
Pranav Dheram, Murugesan Ramakrishnan, Anirudh Raju +6
As for other forms of AI, speech recognition has recently been examined with respect to performance disparities across different user cohorts. One approach to achieve fairness in s…
ILASR: Privacy-Preserving Incremental Learning for Automatic Speech Recognition at Production Scale
Gopinath Chennupati, Milind Rao, Gurpreet Chadha +11
Incremental learning is one paradigm to enable model building and updating at scale with streaming data. For end-to-end automatic speech recognition (ASR) tasks, the absence of hum…
Alexa Teacher Model: Pretraining and Distilling Multi-Billion-Parameter Encoders for Natural Language Understanding Systems
Jack FitzGerald, Shankar Ananthakrishnan, Konstantine Arkoudas +38
We present results from a large-scale experiment on pretraining encoders with non-embedding parameter counts ranging from 700M to 9.3B, their subsequent distillation into smaller m…
Self-Supervised Speech Representation Learning: A Review
Abdelrahman Mohamed, Hung-yi Lee, Lasse Borgholt +9
Although supervised deep learning has revolutionized speech and audio processing, it has necessitated the building of specialist models for individual tasks and application scenari…