Lab
Intelligent Sound Processing Lab (ISP-Lab)
Institution: Shahid Beheshti University
About the lab
Intelligent Sound Processing Laboratory (ISP-Lab)
Research Topics (2018-current):
– Spoken Language Identification (LID)
– Speaker Identification (SID)
– Speaker Diarization (Speaker Segmentation)
– Spoken Keyword Spotting (KWS) & Spoken Term Detection (STD)
– Soken Emotion Recognition (SER)
– Voice Activity Detection (VAD) & Speech Activity Detection (SAD)
– Automatic Speech Recognition (ASR)
– Voice Pathology Detection From Speech
– Automatic Audio Scene Recognition
– Audio Source Separation & Speech Enhancement
– Anomalous Sound Detection (ASD)
– English-to-Persian Voice Actor Recommender System
– Diagnosis of Depression from Speech Signals of Conversations
– Alzheimer’s Dementia Recognition From Speech
– Imagined Speech Detection by EEG signals
– Heart Sound Signal Classification
Research Topics (2018-current):
– Spoken Language Identification (LID)
– Speaker Identification (SID)
– Speaker Diarization (Speaker Segmentation)
– Spoken Keyword Spotting (KWS) & Spoken Term Detection (STD)
– Soken Emotion Recognition (SER)
– Voice Activity Detection (VAD) & Speech Activity Detection (SAD)
– Automatic Speech Recognition (ASR)
– Voice Pathology Detection From Speech
– Automatic Audio Scene Recognition
– Audio Source Separation & Speech Enhancement
– Anomalous Sound Detection (ASD)
– English-to-Persian Voice Actor Recommender System
– Diagnosis of Depression from Speech Signals of Conversations
– Alzheimer’s Dementia Recognition From Speech
– Imagined Speech Detection by EEG signals
– Heart Sound Signal Classification
Featured research (15)
Identification of the spoken languages in an audio file is performed automatically using the spoken language identification (LID) process. In this paper, we proposed a genetic-based fusion method to combine the score probabilities of an x-vector-based acoustic LID (ALID) and a phonetic LID (PLID) system. The ALID system is based on an LDA classifier able to identify different languages using x-vectors, while the PLID system is based on an SVM classifier which takes into account perplexities as its feature vector, which are derived from phone language models utilizing a universal phone recognizer named Allosaurus. With the help of genetic-based fusion, 54 weights will be extracted. Having 27 languages in our database and two different LID systems results in 54 weights for our fusion. The individual results of our acoustic and phonetic LID systems are eventually combined by applying these weights. Based on the experimental results on 27 languages from the NIST-LRE09 database, the fusion of the acoustic system and the phonetic system results in 93.30% accuracy, which has approximately a 21% reduction in identification error to our best baseline system with 91.50% accuracy.
Lab head
![Yasser Shekofteh](https://i1.rgstatic.net/ii/profile.image/535773510619136-1504749767671_Q64/Yasser-Shekofteh.jpg)
Department
- Faculty of Computer Science and Engineering
About Yasser Shekofteh
- Research Fields: - Digital Signal Processing (DSP) and Machine Learning (ML) - Automatic Speech Recognition (ASR), Spoken Term Detection (STD), and Keyword Spotting (KWS) - Voice Commands and Speech Assistant - Speaker Recognition (SRE) and Spoken Language Identification (LID) - Voice Pathology and Sound Heart Detection - Speech Enhancement – noise reduction - Dynamical Systems and Chaos, System Identification, and Parameter Estimation - Robotics {Speech Processing}