4 citations · 7 across the 5 of their papers we have counts for
6 papers
Exploring Teacher-Student Learning Approach for Multi-lingual Speech-to-Intent Classification
Bidisha Sharma, Maulik Madhavi, Xuehao Zhou +1
End-to-end speech-to-intent classification has shown its advantage in harvesting information from both text and speech. In this paper, we study a technique to develop such an end-t…
Knowledge Distillation from BERT Transformer to Speech Transformer for Intent Classification
Yidi Jiang, Bidisha Sharma, Maulik Madhavi +1
End-to-end intent classification using speech has numerous advantages compared to the conventional pipeline approach using automatic speech recognition (ASR), followed by natural l…
Multi-target DoA Estimation with an Audio-visual Fusion Mechanism
Xinyuan Qian, Maulik Madhavi, Zexu Pan +2
Most of the prior studies in the spatial \ac{DoA} domain focus on a single modality. However, humans use auditory and visual senses to detect the presence of sound sources. With th…
Leveraging Acoustic and Linguistic Embeddings from Pretrained speech and language Models for Intent Classification
Bidisha Sharma, Maulik Madhavi, Haizhou Li
Intent classification is a task in spoken language understanding. An intent classification system is usually implemented as a pipeline process, with a speech recognition module fol…
Transformer-based Arabic Dialect Identification
Wanqiu Lin, Maulik Madhavi, Rohan Kumar Das +1
This paper presents a dialect identification (DID) system based on the transformer neural network architecture. The conventional convolutional neural network (CNN)-based systems us…
Speaker-Utterance Dual Attention for Speaker and Utterance Verification
Tianchi Liu, Rohan Kumar Das, Maulik Madhavi +2
In this paper, we study a novel technique that exploits the interaction between speaker traits and linguistic content to improve both speaker verification and utterance verificatio…