activity
20182021
most citedLong-span language modeling for speech recognition

8 citations · 14 across the 4 of their papers we have counts for

collaborators

6 papers

eess.AS20211 cited

Internal Language Model Training for Domain-Adaptive End-to-End Speech Recognition

Zhong Meng, Naoyuki Kanda, Yashesh Gaur +6

The efficacy of external language model (LM) integration with existing end-to-end (E2E) automatic speech recognition (ASR) systems can be improved significantly using the internal…

eess.AS2020

Internal Language Model Estimation for Domain-Adaptive End-to-End Speech Recognition

Zhong Meng, Sarangarajan Parthasarathy, Eric Sun +7

The external language models (LM) integration remains a challenging task for end-to-end (E2E) automatic speech recognition (ASR) which has no clear division between acoustic and la…

cs.CL2020

LSTM-LM with Long-Term History for First-Pass Decoding in Conversational Speech Recognition

Xie Chen, Sarangarajan Parthasarathy, William Gale +2

LSTM language models (LSTM-LMs) have been proven to be powerful and yielded significant performance improvements over count based n-gram LMs in modern speech recognition systems. D…

eess.AS20205 cited

Developing RNN-T Models Surpassing High-Performance Hybrid Models with Customization Capability

Jinyu Li, Rui Zhao, Zhong Meng +8

Because of its streaming nature, recurrent neural network transducer (RNN-T) is a very promising end-to-end (E2E) model that may replace the popular hybrid model for automatic spee…

cs.CL20198 cited

Long-span language modeling for speech recognition

Sarangarajan Parthasarathy, William Gale, Xie Chen +2

We explore neural language modeling for speech recognition where the context spans multiple sentences. Rather than encode history beyond the current sentence using a cache of words…

cs.CL2018

Entity-Aware Language Model as an Unsupervised Reranker

Mohammad Sadegh Rasooli, Sarangarajan Parthasarathy

In language modeling, it is difficult to incorporate entity relationships from a knowledge-base. One solution is to use a reranker trained with global features, in which global fea…