5 citations · 10 across the 5 of their papers we have counts for
5 papers
End-to-end Joint Punctuated and Normalized ASR with a Limited Amount of Punctuated Training Data
Can Cui, Imran Ahamad Sheikh, Mostafa Sadeghi +1
Joint punctuated and normalized automatic speech recognition (ASR) aims at outputing transcripts with and without punctuation and casing. This task remains challenging due to the l…
End-to-end Multichannel Speaker-Attributed ASR: Speaker Guided Decoder and Input Feature Analysis
Can Cui, Imran Ahamad Sheikh, Mostafa Sadeghi +1
We present an end-to-end multichannel speaker-attributed automatic speech recognition (MC-SA-ASR) system that combines a Conformer-based encoder with multi-frame crosschannel atten…
A Cycle-GAN Approach to Model Natural Perturbations in Speech for ASR Applications
Sri Harsha Dumpala, Imran Sheikh, Rupayan Chakraborty +1
Naturally introduced perturbations in audio signal, caused by emotional and physical states of the speaker, can significantly degrade the performance of Automatic Speech Recognitio…
Learning to retrieve out-of-vocabulary words in speech recognition
Imran Sheikh, Irina Illina, Dominique Fohr +1
Many Proper Names (PNs) are Out-Of-Vocabulary (OOV) words for speech recognition systems used to process diachronic audio data. To help recovery of the PNs missed by the system, re…
Automatic Segmentation of Broadcast News Audio using Self Similarity Matrix
Sapna Soni, Ahmed Imran, Sunil Kumar Kopparapu
Generally audio news broadcast on radio is com- posed of music, commercials, news from correspondents and recorded statements in addition to the actual news read by the newsreader.…