research
∙
09/19/2023
Discrete Audio Representation as an Alternative to Mel-Spectrograms for Speaker and Speech Recognition
Discrete audio representation, aka audio tokenization, has seen renewed ...
share
research
∙
09/11/2023
Enhancing Speaker Diarization with Large Language Models: A Contextual Beam Search Approach
Large language models (LLMs) have shown great promise for capturing cont...
research
∙
06/14/2023
Towards training Bilingual and Code-Switched Speech Recognition models from Monolingual data sources
Multilingual Automatic Speech Recognition (ASR) models are capable of tr...
research
∙
09/30/2021
Phonetic Word Embeddings
This work presents a novel methodology for calculating the phonetic simi...
research
∙
07/16/2019
Towards Adapting NMF Dictionaries Using Total Variability Modeling for Noise-Robust Acoustic Features
We propose an algorithm to extract noise-robust acoustic features from n...
research
∙
07/15/2019
Investigating Target Set Reduction for End-to-End Speech Recognition of Hindi-English Code-Switching Data
End-to-end (E2E) systems are fast replacing the conventional systems in ...
research
∙
07/15/2019
Joint Language Identification of Code-Switching Speech using Attention based E2E Network
Language identification (LID) has relevance in many speech processing ap...
research
∙
09/24/2018