Shatrughan Singh — accepted AI-conference papers

2024

Robust Speaker Personalisation Using Generalized Low-Rank Adaptation for Automatic Speech Recognition

Arun Baby, George Joseph, Shatrughan Singh

ICASSP 2024accepted

For voice assistant systems, personalizing automated speech recognition (ASR) to a customer is the proverbial holy grail. Careful selection of hyper-parameters will be necessary for fine-tuning a larger ASR model with little speaker data. It is demonstrated that low-rank adaptation (LoRA) is a usefu…

Cited by 0 Source ↗Scholar ↗

2021

Neural Utterance Confidence Measure for RNN-Transducers and Two Pass Models

Ashutosh Gupta, Ankur Kumar, Dhananjaya Gowda, Kwangyoun Kim, Sachin Singh, Shatrughan Singh +1

ICASSP 2021accepted

In this paper, we propose methods to compute confidence score on the predictions made by an end-to-end speech recognition model in a 2-pass framework. We use RNN-Transducer for a streaming model, and an attention-based decoder for the second pass model. We use neural technique to compute the confide…

Cited by 0 Source ↗Scholar ↗