Professional AssociationsProfessional Associations: International Speech Communication Association (ISCA)
In 1996, Kelvin Yong Qin join in IBM Research - China after earning his Ph.D degree in speech signal processing field from Institute of Acoustic (IOA) of Chinese Academy of Sciences. During the period between 1996 and 2005, Kelvin's work widely covered research and development activities of IBM speech products, including the first Mandarin ViaVoice Dictation System, IBM ViaVoice Telephony Runtime & Tools, IBM Embedded ViaVoice, IBM Websphere Voice Server, etc.
Since 2005, Kelvin made key technical contributions and led team to develop Mandarin speech transcription system. IBM Mandarin speech transcription system was rated as one of the most accurate Mandarin speech transcription systems in the world according to the benchmark evaluation organized by DARPA GALE committee. Kelvin designed and implemented the first Mandarin speaker independent training pipeline, speaker adaptive training pipeline, voice & text data pre-processing tool, cross-system adaptation, and snippet-based performance evaluation tool.
From 2009, Kelvin led team to develop a set of speech solutions, the most famous one is iTrans, which is a speech infrastructure to enable speech services through Cloud. iTrans is widely applied in IBM internal solutions and external applications in customer sites. iTrans enabled enterprise's call center to unlock new intelligence from multimedia data.
Currently, Kelvin is the senior manager of IBM Research-China’s Information and User Technology (IUT) department. IUT's research efforts cover Information Analytics and HCI.
Information Analytics focuses on analysis and management of information that is embedded in structured, semi-structured and unstructured data. The information analytics research includes natural language processing, rich-media analysis, social media analysis, enterprise search, sentiment analysis and data cleansing.
Human Computer Interaction research focuses on the research and development of the next-generation, intelligent user interaction and social collaboration technologies with an emphasis on user-centered information interaction paradigms, methodologies, metaphors, and technologies that assist individual users in their information access, analysis, and synthesis.