Field dossier · from the corpus

Acoustic model

0predicted collisions

Where this field is predicted to collide

No open collisions on this field in the current run.

Most cited work

Listen, attend and spell: A neural network for large vocabulary conversational speech recognition

20162,356 citationsDOI ↗

Exploring architectures, data and units for streaming end-to-end speech recognition with RNN-transducer

2017371 citationsDOI ↗

The microsoft 2016 conversational speech recognition system

2017337 citationsDOI ↗

Signals

3

Papers · in corpus

3.1k

Citations · corpus total

0.0%

Recent share · since 2024

2016–2017

Span · publication years

Who is doing the work

Google (United States)US2
TU WienAT1
Brain (Germany)DE1
University of California, San FranciscoUS1
Brown UniversityUS1
University of Illinois Urbana-ChampaignUS1
Volkswagen Group (Germany)DE1
Microsoft Research (United Kingdom)GB1

Most published researchers

Michael L. Seltzer1
Geoffrey Zweig1
Jasha Droppo1
Andreas Stolcke1
Wayne Xiong1
Xuedong Huang1

Already lives beside

Fields this one already co-publishes with. A predicted collision is a departure from this neighbourhood, not an extension of it.

Language model2 Word error rate2 Speech recognition2 Convolutional neural network1 Connectionism1 Dictation1 Recurrent neural network1 NIST1 Benchmark (surveying)1 Task (project management)1