Search Results for author: Yuzong Liu

Found 9 papers, 3 papers with code

DeCoAR 2.0: Deep Contextualized Acoustic Representations with Vector Quantization

1 code implementation11 Dec 2020 Shaoshi Ling, Yuzong Liu

In speech representation learning, a large amount of unlabeled data is used in a self-supervised manner to learn a feature representation.

Quantization Representation Learning +1

Streaming Language Identification using Combination of Acoustic Representations and ASR Hypotheses

no code implementations1 Jun 2020 Chander Chandak, Zeynab Raeesy, Ariya Rastrow, Yuzong Liu, Xiangyang Huang, Siyu Wang, Dong Kwon Joo, Roland Maas

A common approach to solve multilingual speech recognition is to run multiple monolingual ASR systems in parallel and rely on a language identification (LID) component that detects the input language.

Language Identification Speech Recognition

BERTphone: Phonetically-Aware Encoder Representations for Utterance-Level Speaker and Language Recognition

1 code implementation30 Jun 2019 Shaoshi Ling, Julian Salazar, Yuzong Liu, Katrin Kirchhoff

We introduce BERTphone, a Transformer encoder trained on large speech corpora that outputs phonetically-aware contextual representation vectors that can be used for both speaker and language recognition.

Representation Learning Speaker Recognition +1

End-to-end Anchored Speech Recognition

no code implementations6 Feb 2019 Yiming Wang, Xing Fan, I-Fan Chen, Yuzong Liu, Tongfei Chen, Björn Hoffmeister

The anchored segment refers to the wake-up word part of an audio stream, which contains valuable speaker information that can be used to suppress interfering speech and background noise.

Multi-Task Learning Speech Recognition

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