Search Results for author: Dhananjaya Gowda

Found 11 papers, 0 papers with code

Multi-stage Progressive Compression of Conformer Transducer for On-device Speech Recognition

no code implementations1 Oct 2022 Jash Rathod, Nauman Dawalatabad, Shatrughan Singh, Dhananjaya Gowda

Knowledge distillation (KD) is a popular model compression approach that has shown to achieve smaller model size with relatively lesser degradation in the model performance.

Automatic Speech Recognition Knowledge Distillation +2

Two-Pass End-to-End ASR Model Compression

no code implementations8 Jan 2022 Nauman Dawalatabad, Tushar Vatsal, Ashutosh Gupta, Sungsoo Kim, Shatrughan Singh, Dhananjaya Gowda, Chanwoo Kim

With the use of popular transducer-based models, it has become possible to practically deploy streaming speech recognition models on small devices [1].

Knowledge Distillation Model Compression +2

Formant Tracking Using Quasi-Closed Phase Forward-Backward Linear Prediction Analysis and Deep Neural Networks

no code implementations5 Jan 2022 Dhananjaya Gowda, Bajibabu Bollepalli, Sudarsana Reddy Kadiri, Paavo Alku

Formant tracking is investigated in this study by using trackers based on dynamic programming (DP) and deep neural nets (DNNs).

A comparison of streaming models and data augmentation methods for robust speech recognition

no code implementations19 Nov 2021 Jiyeon Kim, Mehul Kumar, Dhananjaya Gowda, Abhinav Garg, Chanwoo Kim

However, we observe that training of MoChA models seems to be more sensitive to various factors such as the characteristics of training sets and the incorporation of additional augmentations techniques.

Data Augmentation Robust Speech Recognition +1

Semi-supervised transfer learning for language expansion of end-to-end speech recognition models to low-resource languages

no code implementations19 Nov 2021 Jiyeon Kim, Mehul Kumar, Dhananjaya Gowda, Abhinav Garg, Chanwoo Kim

To improve the accuracy of a low-resource Italian ASR, we leverage a well-trained English model, unlabeled text corpus, and unlabeled audio corpus using transfer learning, TTS augmentation, and SSL respectively.

Data Augmentation speech-recognition +2

Streaming end-to-end speech recognition with jointly trained neural feature enhancement

no code implementations4 May 2021 Chanwoo Kim, Abhinav Garg, Dhananjaya Gowda, Seongkyu Mun, Changwoo Han

In this paper, we present a streaming end-to-end speech recognition model based on Monotonic Chunkwise Attention (MoCha) jointly trained with enhancement layers.

speech-recognition Speech Recognition

A review of on-device fully neural end-to-end automatic speech recognition algorithms

no code implementations14 Dec 2020 Chanwoo Kim, Dhananjaya Gowda, Dongsoo Lee, Jiyeon Kim, Ankur Kumar, Sungsoo Kim, Abhinav Garg, Changwoo Han

Conventional speech recognition systems comprise a large number of discrete components such as an acoustic model, a language model, a pronunciation model, a text-normalizer, an inverse-text normalizer, a decoder based on a Weighted Finite State Transducer (WFST), and so on.

Automatic Speech Recognition speech-recognition

Attention based on-device streaming speech recognition with large speech corpus

no code implementations2 Jan 2020 Kwangyoun Kim, Kyungmin Lee, Dhananjaya Gowda, Junmo Park, Sungsoo Kim, Sichen Jin, Young-Yoon Lee, Jinsu Yeo, Daehyun Kim, Seokyeong Jung, Jungin Lee, Myoungji Han, Chanwoo Kim

In this paper, we present a new on-device automatic speech recognition (ASR) system based on monotonic chunk-wise attention (MoChA) models trained with large (> 10K hours) corpus.

Automatic Speech Recognition Data Augmentation +2

Improved Multi-Stage Training of Online Attention-based Encoder-Decoder Models

no code implementations28 Dec 2019 Abhinav Garg, Dhananjaya Gowda, Ankur Kumar, Kwangyoun Kim, Mehul Kumar, Chanwoo Kim

In this paper, we propose a refined multi-stage multi-task training strategy to improve the performance of online attention-based encoder-decoder (AED) models.

Language Modelling Multi-Task Learning

power-law nonlinearity with maximally uniform distribution criterion for improved neural network training in automatic speech recognition

no code implementations22 Dec 2019 Chanwoo Kim, Mehul Kumar, Kwangyoun Kim, Dhananjaya Gowda

With the power function-based MUD, we apply a power-function based nonlinearity where power function coefficients are chosen to maximize the likelihood assuming that nonlinearity outputs follow the uniform distribution.

Automatic Speech Recognition speech-recognition

end-to-end training of a large vocabulary end-to-end speech recognition system

no code implementations22 Dec 2019 Chanwoo Kim, Sungsoo Kim, Kwangyoun Kim, Mehul Kumar, Jiyeon Kim, Kyungmin Lee, Changwoo Han, Abhinav Garg, Eunhyang Kim, Minkyoo Shin, Shatrughan Singh, Larry Heck, Dhananjaya Gowda

Our end-to-end speech recognition system built using this training infrastructure showed a 2. 44 % WER on test-clean of the LibriSpeech test set after applying shallow fusion with a Transformer language model (LM).

Data Augmentation speech-recognition +1

Cannot find the paper you are looking for? You can Submit a new open access paper.