activity
20192021
most citedAccent-Robust Automatic Speech Recognition Using Supervised and Unsupervised Wav2vec Embeddings

11 citations · 28 across the 10 of their papers we have counts for

collaborators
Showing eess.ASShow all

8 papers · 1 filter

eess.AS202111 cited

Accent-Robust Automatic Speech Recognition Using Supervised and Unsupervised Wav2vec Embeddings

Jialu Li, Vimal Manohar, Pooja Chitkara +5

Speech recognition models often obtain degraded performance when tested on speech with unseen accents. Domain-adversarial training (DAT) and multi-task learning (MTL) are two commo…

eess.AS20211 cited

On lattice-free boosted MMI training of HMM and CTC-based full-context ASR models

Xiaohui Zhang, Vimal Manohar, David Zhang +7

Hybrid automatic speech recognition (ASR) models are typically sequentially trained with CTC or LF-MMI criteria. However, they have vastly different legacies and are usually implem…

eess.AS20211 cited

Kaizen: Continuously improving teacher using Exponential Moving Average for semi-supervised speech recognition

Vimal Manohar, Tatiana Likhomanenko, Qiantong Xu +5

In this paper, we introduce the Kaizen framework that uses a continuously improving teacher to generate pseudo-labels for semi-supervised speech recognition (ASR). The proposed app…

eess.AS2020

Benchmarking LF-MMI, CTC and RNN-T Criteria for Streaming ASR

Xiaohui Zhang, Frank Zhang, Chunxi Liu +8

In this work, to measure the accuracy and efficiency for a latency-controlled streaming automatic speech recognition (ASR) application, we perform comprehensive evaluations on thre…

eess.AS2020

Contextual RNN-T For Open Domain ASR

Mahaveer Jain, Gil Keren, Jay Mahadeokar +3

End-to-end (E2E) systems for automatic speech recognition (ASR), such as RNN Transducer (RNN-T) and Listen-Attend-Spell (LAS) blend the individual components of a traditional hybri…

eess.AS20202 cited

Faster, Simpler and More Accurate Hybrid ASR Systems Using Wordpieces

Frank Zhang, Yongqiang Wang, Xiaohui Zhang +3

In this work, we first show that on the widely used LibriSpeech benchmark, our transformer-based context-dependent connectionist temporal classification (CTC) system produces state…