• Papers &
• Ph.D. Theses
• Speech Lab
• Events & Links
• Pet Gallery
• NLP Group
Spoken Language Processing Group
The Spoken Language Processing Group at Columbia, which was established by Prof. Julia Hirschberg, includes PhD, masters, and undergraduate students and a postdoc. We have done research recently in emotion, sentiment, deception, charisma, trust and mistrust in speech, text, and video, in hateful and abusive speech, keyword speech search, code-switching, dialogue systems, and radicalization and fake information in videos. We also pursue work in speech generation, particularly in the appropriate assignment of prosody for text-to-speech synthesis in English and Low-Resource Languages.
We collaborate closely with other members of the Columbia NLP Group (headed by Prof. Kathleen McKeown) and faculty in other disciplines, including journalism, English, and history. We also have close research relationships with other universities and research labs and enjoy funding from NSF, DARPA, and AFOSR.
We have a laboratory in Schapiro CEPSR 7LW3,
where we perform laboratory studies on human speech production, analyze
speech, and build speech technologies.
Resources and Facilities
The SLPG has facilities for studio quality audio recording, for video
recording, and for state-of-the-art computing.
Sound and Video
Speech data is collected using a Tascam digital audio recorder and Crown
headworn microphones. Recording is done in a double-walled sound proof
booth generously donated by Agere Systems, through the kindness of Peter
Kroon. Video equipment includes a Hitachi DVD Camcorder.
The group has 5 state-of-the-art GPU machines, and has access to Columbia
University's High Performance Computing clusters Habanero and Terremoto.
The group maintains a growing collection of speech corpora and other
databases, collected both at Columbia and elsewhere.