Julius - an open source real-time large vocabulary recognition engine

By Akinobu Lee, Tatsuya Kawahara, Kiyohiro Shikano. 2001

660 citations recorded by the source corpus.

EUROSPEECH2001: the 7th European Conference on Speech Communication and Technology, September 3-7, 2001, Aalborg, Denmark.

Subfields: Computer Networks and Communications, Information Systems, Safety Research

How researchers see this paper

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

In Computer Networks and Communications

1. Graham W. Taylor
2. Florian Nebout
3. Satoshi Nakamura
4. Tatsuya Kawahara

In Information Systems

1. Graham W. Taylor
2. Florian Nebout
3. Satoshi Nakamura
4. Hermann Ney
5. Tatsuya Kawahara
6. Ian Lane
7. Sharath Adavanne

In Safety Research

1. Graham W. Taylor
2. Florian Nebout
3. Tatsuya Kawahara
4. Adithya Renduchintala

Citations in the corpus

• ESPnet: End-to-End Speech Processing Toolkit (2018, background): “Especially, these efforts have been driven by popular products including Google voice search, Amazon Alexa, and Apple Siri and open source activities including Kaldi [1], HTK [2], Sphinx [3], Julius [4], RASR [5] in addition to general research activities.”
• Improving Speech Prosody of Audiobook Text-To-Speech Synthesis with Acoustic and Textual Contexts (2022, methodology): “For the forced alignment we used Julius [24] to get the duration of each phoneme.”
• TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 1 ModDrop (2018, positive): “A baseline has also been created for the audio channel, where we compare the proposed deep learning approach to a traditional phoneme recognition framework, as described in [48], and implemented with the Julius engine [59].”
• The Kaldi Speech Recognition Toolkit (2011, background): “Notable among these are: HTK [1], Julius [2] (both written in C), Sphinx-4 [3] (written in Java), and the RWTH ASR toolkit [4] (written in C++).”
• RASR/NN: The RWTH neural network toolkit for speech recognition (2014, background): “Index Terms— speech recognition, acoustic modeling, neural networks, GPU, open source, RASR”
• Out-of-Domain Utterance Detection Using Classification Confidences of Multiple Topics (2007, methodology): “ASR was performed with our Julius recognition engine [32].”
• Recent Development of Open-Source Speech Recognition Engine Julius (2009, neutral): “Performance: • Real time recognition of 60k-word dictation on PCs, PDAs and handheld devices • Small footprint (about 60MB for 20k-word Japanese tri-phone dictation, including N-gram of 38MB on memory)”
• Train&align: A new online tool for automatic phonetic alignment (2012, methodology): “HMM-based recognition toolkits like HTK [10] or Julius [11].”