Vimal Manohar

Sort by:

Purely Sequence-Trained Neural Networks for ASR Based on Lattice-Free MMI

Daniel Povey, Vijayaditya Peddinti, +5 authors Sanjeev Khudanpur
INTERSPEECH
2016

In this paper we describe a method to perform sequencediscriminative training of neural network acoustic models without the need for frame-level cross-entropy pre-training. We use the lattice-free… (More)

An Exploration of Dropout with LSTMs

Gaofeng Cheng, Vijayaditya Peddinti, Daniel Povey, Vimal Manohar, Sanjeev Khudanpur, Yonghong Yan
INTERSPEECH
2017

Long Short-Term Memory networks (LSTMs) are a component of many state-of-the-art DNN-based speech recognition systems. Dropout is a popular method to improve generalization in DNN training. In this… (More)

A keyword search system using open source software

Jan Trmal, Guoguo Chen, +9 authors Florian Metze
2014 IEEE Spoken Language Technology Workshop…
2014

Provides an overview of a speech-to-text (STT) and keyword search (KWS) system architecture build primarily on the top of the Kaldi toolkit and expands on a few highlights. The system was developed… (More)

Acoustic Modelling from the Signal Domain Using CNNs

Pegah Ghahremani, Vimal Manohar, Daniel Povey, Sanjeev Khudanpur
INTERSPEECH
2016

Most speech recognition systems use spectral features based on fixed filters, such as MFCC and PLP. In this paper, we show that it is possible to achieve state of the art results by making the… (More)

JHU ASpIRE system: Robust LVCSR with TDNNS, iVector adaptation and RNN-LMS

Vijayaditya Peddinti, Guoguo Chen, Vimal Manohar, Tom Ko, Daniel Povey, Sanjeev Khudanpur
2015 IEEE Workshop on Automatic Speech…
2015

Multi-style training, using data which emulates a variety of possible test scenarios, is a popular approach towards robust acoustic modeling. However acoustic models capable of exploiting large… (More)

Adapting ASR for under-resourced languages using mismatched transcriptions

Chunxi Liu, Preethi Jyothi, +5 authors Sanjeev Khudanpur
2016 IEEE International Conference on Acoustics…
2016

Mismatched transcriptions of speech in a target language refers to transcriptions provided by people unfamiliar with the language, using English letter sequences. In this work, we demonstrate the… (More)

ASR for Under-Resourced Languages From Probabilistic Transcription

Mark A. Hasegawa-Johnson, Preethi Jyothi, +13 authors Adrian K. C. Lee
IEEE/ACM Transactions on Audio, Speech, and…
2017

In many under-resourced languages it is possible to find text, and it is possible to find speech, but transcribed speech suitable for training automatic speech recognition ASR is unavailable. In the… (More)

Acoustic modeling using transform-based phone-cluster adaptive training

Vimal Manohar, Srinivas C. Bhargav, Srinivasan Umesh
2013 IEEE Workshop on Automatic Speech…
2013

In this paper, we propose a new acoustic modeling technique called the Phone-Cluster Adaptive Training. In this approach, the parameters of context-dependent states are obtained by the linear… (More)

Investigation of transfer learning for ASR using LF-MMI trained neural networks

Pegah Ghahremani, Vimal Manohar, Hossein Hadian, Daniel Povey, Sanjeev Khudanpur
2017 IEEE Automatic Speech Recognition and…
2017

It is common in applications of ASR to have a large amount of data out-of-domain to the test data and a smaller amount of in-domain data similar to the test data. In this paper, we investigate… (More)

Far-Field ASR Without Parallel Data

Vijayaditya Peddinti, Vimal Manohar, Yiming Wang, Daniel Povey, Sanjeev Khudanpur
INTERSPEECH
2016

In far-field speech recognition systems, training acoustic models with alignments generated from parallel close-talk microphone data provides significant improvements. However it is not practical to… (More)

Filter Results:

Publication Year

Publication Type

Co-author

Journals and Conferences