Center for Language and Speech Processing

Language Modeling for Conversational Speech Recognition

Goals:

1) Creating language models that are attuned to spontaneous conversations.
“There is more to conversational speech than Dysfluencies.”

2) Beyond mere word-based transcription:
identifying and cleaning up disfluencies.
transforming the output into “simplified English”.

Project Page & Team Report

 

Team Members
Senior Members
Rajeev AgarwalTI
Bill ByrneJHU
Mark LibermanUPenn
Roni RosenfeldCMU
Liz ShribergSRI
Jack UnverferthDoD
Enrique VidalValencia-Spain
Graduate Students
Dimitra VergyriCLSP
Rukmini IyerBBN
Subscribe to the CLSP Seminars Mailing List

Upcoming Seminars

Nov
3
Mon
12:00 pm The Translation Barrier Hypothes... @ Hackerman Hall B17
The Translation Barrier Hypothes... @ Hackerman Hall B17
Nov 3 @ 12:00 pm – 1:15 pm
Abstract Multilingual generation with large language models (LLMs) is often of poor quality for mid- to low-resource languages, but the causes for this are not well-understood. We first demonstrate the existence of an implicit task-solving–>[...]
Nov
7
Fri
12:00 pm Scaling Artificial Intelligence ... @ Hackerman Hall B17
Scaling Artificial Intelligence ... @ Hackerman Hall B17
Nov 7 @ 12:00 pm – 1:15 pm
Abstract Early tumor detection saves lives. Each year, more than 300 million computed tomography (CT) scans are performed worldwide, offering a vast opportunity for effective cancer screening. However, detecting small or early-stage tumors on these[...]
Nov
10
Mon
12:00 pm SPS Webinar: Minor Manipulations... @ Hackerman Hall B17
SPS Webinar: Minor Manipulations... @ Hackerman Hall B17
Nov 10 @ 12:00 pm – 1:15 pm
Abstract Speech can easily be manipulated through techniques, such as text-to-speech synthesis, voice conversion, replay, tampering, adversarial attacks, and more. However, when the manipulation is applied only to a minor portion of an audio, the[...]

Center for Language and Speech Processing