Home page

Research

Publications

Teaching

Public Resources

Public Profiles

Giampiero Salvi

Royal Institute of Technology
School of Computer Science and Communication
Speech, Music and Hearing
Lindstedtsvägen 24
SE-100 44, Stockholm, Sweden

mail: giampi [at] kth [dot] se
phone: +46 8 790 7894
fax: +46 8 790 7854

Research interests

I work with machine learning, speech technology and cognitive systems. During my PhD studies I developed the low latency phoneme recogniser in the Synface prototype. In the BioASU project I have been involved with modelling early language acquisition and multi-modal perception.

I recently participated in the Crosstalks Show The power of the human voice. Click on the link to see program.

PhD Students

Selected Publications (full list here)

Vanhainen, N., & Salvi, G. (2014). Pattern Discovery in Continuous Speech Using Block Diagonal Infinite HMM. In Proceedings of ICASSP. Florence, Italy. [pdf]

Salvi, G., Montesano, L., Bernardino, A., & Santos-Victor, J. (2012). Language bootstrapping: Learning word meanings from perception-action association. IEEE Transactions on Systems, Man, and Cybernetics, Part B, 42(3), 660-671. [abstract] [pdf]

Ananthakrishnan, G., & Salvi, G. (2011). Using Imitation to learn Infant-Adult Acoustic Mappings. In Proceedings of Interspeech (pp. 765-768). Florence, Italy. [abstract] [pdf]

Salvi, G., Beskow, J., Al Moubayed, S., & Granström, B. (2009). SynFace—Speech-Driven Facial Animation for Virtual Speech-Reading Support. EURASIP Journal on Audio, Speech, and Music Processing, 2009. [abstract] [pdf]