Publications

Sound event detection using weakly labeled dataset with stacked convolutional and recurrent neural network
Sharath Adavanne and Tuomas Virtanen
Detection and Classification of Acoustic Scenes and Events (DCASE 2017)

Automated audio captioning with recurrent neural networks
Konstantinos Drossos*, Sharath Adavanne* and Tuomas Virtanen
IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA 2017) [Online demo]

Stacked convolutional and recurrent neural networks for bird audio detection
Sharath Adavanne, Konstantinos Drossos, Emre Cakir and Tuomas Virtanen
European Signal Processing Conference (EUSIPCO 2017) [Poster]

Convolutional recurrent neural networks for bird audio detection
Emre Cakir, Sharath Adavanne, Giambattista Parascandolo, Konstantinos Drossos and Tuomas Virtanen
European Signal Processing Conference (EUSIPCO 2017)

Stacked convolutional and recurrent neural networks for music emotion recognition
Miroslav Malik*, Sharath Adavanne*, Konstantinos Drossos, Tuomas Virtanen, Dasa Ticha, Roman Jarina
Sound and Music Computing Conference (SMC 2017)

Assessment of support vector machines and convolutional neural networks to detect snoring using Emfit mattress
Jose M. Perez-Macias, Sharath Adavanne, Jari Viik, Alpo Värri, Sari-Leena Himanen, and Mirja Tenhunen
The Engineering in Medicine and Biology Conference (EMBC 2017)

Sound event detection using spatial features and convolutional recurrent neural network
Sharath Adavanne, Pasi Pertila and Tuomas Virtanen
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2017) [Poster]

Sound event detection in multichannel audio using spatial and harmonic features
Sharath Adavanne, Giambattista Parascandolo, Pasi Pertila, Toni Heittola and Tuomas Virtanen
Detection and Classification of Acoustic Scenes and Events (DCASE 2016) [Poster]

Room surface estimation using reflection coefficients measured in-situ
Sharath Adavanne
MSc thesis, Tampere University of Technology, Finland 2011

* Equally contributing authors in the paper


Research Challenges

Sound event detection in real life audio
Multi-source sound event detection in real life conditions, where the events can occur in both isolation or overlapped. The performance of systems were evaluated based on the error rate, which is zero for an ideal system. The submitted system performed the best among 13 competitors in the challenge. [Results] [Submitted system description]
Sharath Adavanne and Tuomas Virtanen
Detection and Classification of Acoustic Scenes and Events (DCASE 2017)

Large-scale weakly supervised sound event detection for smart cars
Large-scale detection of sound events using weakly labeled training data. The performance of systems were evaluated based on the error rate, which is zero for an ideal system. The submitted system fared fifth of eight competitors in the challenge. [Results] [Submitted system description]
Sharath Adavanne and Tuomas Virtanen
Detection and Classification of Acoustic Scenes and Events (DCASE 2017)

QMUL bird audio detection challenge 2016
Detecting bird sounds in audio is an important task for automatic wildlife monitoring. In this task, given a short audio recording, a binary decision for the presence/absence of bird sound has to be made. Two systems were submitted, which fared second and fifth among 30 competitors in the challenge. [Results] [Submitted system 1 description] [Submitted system 2 description]
Sharath Adavanne, Emre Cakir, Konstantinos Drossos, Giambattista Parascandolo, and Tuomas Virtanen

Sound event detection in real life audio
Multi-source sound event detection in real life conditions, where the events can occur in both isolation or overlapped. The performance of systems were evaluated based on the error rate, which is zero for an ideal system. The submitted system performed the best among 17 competitors in the challenge. [Results] [Submitted system description]
Sharath Adavanne, Giambattista Parascandolo, Pasi Pertila, Toni Heittola and Tuomas Virtanen
Detection and Classification of Acoustic Scenes and Events (DCASE 2016)

Singing voice separation
Blind separation of singer's voice from pop recordings.The submitted system fared in the top systems with good signal-to-distortion ratio for both voice and residual. [Results] [Submitted system description]
Preeti Rao, Nagesh Nayak and Sharath Adavanne
Music Information Retrieval Evaluation eXchange (MIREX 2014)


Patent

Music performance system and method thereof
US 20170140745 A1
Nagesh Nayak, Sharath Adavanne, Preeti Rao, Sachin Pant, Sujeet Kini, Vishweshwara Rao