Background and activities
Giampiero Salvi is Professor at the Department of Electronic Systems. He is a member of the Signal Processing Group. He is also an Associate Professor with KTH Royal Institute of Technology in Sweden. Professor Salvi has an M.Sc. from the Department of Electrical Engineering at La Sapienza University in Rome, Italy, and a PhD from the Department of Computer Science and Electrical Engineering at KTH Royal Institue of Technology in Sweden.
- Machine Learning
- Speech Technology
- Cognitive Systems
Scientific, academic and artistic work
Displaying a selection of activities. See all publications in the database
- (2019) Beyond the Self: Using Grounded Affordances to Interpret and Describe Others' Actions. IEEE Transactions on Cognitive and Developmental Systems.
- (2019) Effect of vowel context in cepstral and entropy analysis of pathological voices. Biomedical Signal Processing and Control. vol. 47.
- (2019) Self-Supervised Vision-Based Detection of the Active Speaker as Support for Socially-Aware Language Acquisition. IEEE Transactions on Cognitive and Developmental Systems.
- (2019) Modeling of Human Visual Attention in Multiparty Open-World Dialogues. ACM Transactions on Human-Robot Interaction. vol. 8 (2).
- (2015) Acoustic and perceptual evaluation of category goodness of /t/ and /k/ in typical and misarticulated children's speech. Journal of the Acoustical Society of America. vol. 137 (6).
- (2013) On mispronunciation analysis of individual foreign speakers using auditory periphery models. Speech Communication. vol. 55 (5).
- (2013) Semi-supervised methods for exploring the acoustics of simple productive feedback. Speech Communication. vol. 55 (3).
- (2012) Language bootstrapping: Learning Word Meanings From Perception-Action Association. IEEE Transactions on Cybernetics. vol. 42 (3).
- (2009) SynFace-Speech-Driven Facial Animation for Virtual Speech-Reading Support. EURASIP Journal on Audio, Speech, and Music Processing. vol. 2009.
- (2006) Dynamic behaviour of connectionist speech recognition with strong latency constraints. Speech Communication. vol. 48 (7).
- (2006) Segment boundary detection via class entropy measurements in connectionist phoneme recognition. Speech Communication. vol. 48 (12).
- (2004) Intelligibility of an ASR-controlled synthetic talking face. Journal of the Acoustical Society of America. vol. 115 (5).