Cross-lingual Knowledge Transfer and Iterative Pseudo-labeling for Low-Resource Speech Recognition with Transducers

no code implementations • 23 May 2023 • Jan Silovsky, Liuhui Deng, Arturo Argueta, Tresi Arvizo, Roger Hsiao, Sasha Kuznietsov, Yiu-Chang Lin, Xiaoqiang Xiao, Yuanyuan Zhang

Voice technology has become ubiquitous recently.

Automatic Speech Recognition speech-recognition +2

Neural Transducer Training: Reduced Memory Consumption with Sample-wise Computation

no code implementations • 29 Nov 2022 • Stefan Braun, Erik McDermott, Roger Hsiao

As a highlight, we manage to compute the transducer loss and gradients for a batch size of 1024, and audio length of 40 seconds, using only 6 GB of memory.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Variable Attention Masking for Configurable Transformer Transducer Speech Recognition

no code implementations • 2 Nov 2022 • Pawel Swietojanski, Stefan Braun, Dogan Can, Thiago Fraga da Silva, Arnab Ghoshal, Takaaki Hori, Roger Hsiao, Henry Mason, Erik McDermott, Honza Silovsky, Ruchir Travadi, Xiaodan Zhuang

This work studies the use of attention masking in transformer transducer based speech recognition for building a single configurable model for different deployment scenarios.

speech-recognition Speech Recognition

Optimizing Bilingual Neural Transducer with Synthetic Code-switching Text Generation

no code implementations • 21 Oct 2022 • Thien Nguyen, Nathalie Tran, Liuhui Deng, Thiago Fraga da Silva, Matthew Radzihovsky, Roger Hsiao, Henry Mason, Stefan Braun, Erik McDermott, Dogan Can, Pawel Swietojanski, Lyan Verwimp, Sibel Oyman, Tresi Arvizo, Honza Silovsky, Arnab Ghoshal, Mathieu Martel, Bharat Ram Ambati, Mohamed Ali

Code-switching describes the practice of using more than one language in the same sentence.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

Bilingual End-to-End ASR with Byte-Level Subwords

no code implementations • 1 May 2022 • Liuhui Deng, Roger Hsiao, Arnab Ghoshal

In this paper, we investigate how the output representation of an end-to-end neural network affects multilingual automatic speech recognition (ASR).

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Online Automatic Speech Recognition with Listen, Attend and Spell Model

no code implementations • 12 Aug 2020 • Roger Hsiao, Dogan Can, Tim Ng, Ruchir Travadi, Arnab Ghoshal

The Listen, Attend and Spell (LAS) model and other attention-based automatic speech recognition (ASR) models have known limitations when operated in a fully online mode.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Improving Language Identification for Multilingual Speakers

no code implementations • 29 Jan 2020 • Andrew Titus, Jan Silovsky, Nanxin Chen, Roger Hsiao, Mary Young, Arnab Ghoshal

Spoken language identification (LID) technologies have improved in recent years from discriminating largely distinct languages to discriminating highly similar languages or even dialects of the same language.

Language Identification Spoken language identification

Migrating Monarch Butterfly Localization Using Multi-Sensor Fusion Neural Networks

no code implementations • 14 Dec 2019 • Mingyu Yang, Roger Hsiao, Gordy Carichner, Katherine Ernst, Jaechan Lim, Delbert A. Green II, Inhee Lee, David Blaauw, Hun-Seok Kim

Details of Monarch butterfly migration from the U. S. to Mexico remain a mystery due to lack of a proper localization technology to accurately localize and track butterfly migration.

Sensor Fusion