Deploying self-supervised learning in the wild for hybrid automatic speech recognition

no code implementations • 17 May 2022 • Mostafa Karimi, Changliang Liu, Kenichi Kumatani, Yao Qian, Tianyu Wu, Jian Wu

Self-supervised learning (SSL) methods have proven to be very successful in automatic speech recognition (ASR).

Automatic Speech Recognition Automatic Speech Recognition (ASR) +4

Exploring Transformers for Large-Scale Speech Recognition

no code implementations • 19 May 2020 • Liang Lu, Changliang Liu, Jinyu Li, Yifan Gong

While recurrent neural networks still largely define state-of-the-art speech recognition systems, the Transformer network has been proven to be a competitive alternative, especially in the offline condition.

speech-recognition Speech Recognition

L-Vector: Neural Label Embedding for Domain Adaptation

no code implementations • 25 Apr 2020 • Zhong Meng, Hu Hu, Jinyu Li, Changliang Liu, Yan Huang, Yifan Gong, Chin-Hui Lee

We propose a novel neural label embedding (NLE) scheme for the domain adaptation of a deep neural network (DNN) acoustic model with unpaired data samples from source and target domains.

Domain Adaptation

Advances in Online Audio-Visual Meeting Transcription

no code implementations • 10 Dec 2019 • Takuya Yoshioka, Igor Abramovski, Cem Aksoylar, Zhuo Chen, Moshe David, Dimitrios Dimitriadis, Yifan Gong, Ilya Gurvich, Xuedong Huang, Yan Huang, Aviv Hurvitz, Li Jiang, Sharon Koubi, Eyal Krupka, Ido Leichter, Changliang Liu, Partha Parthasarathy, Alon Vinnikov, Lingfeng Wu, Xiong Xiao, Wayne Xiong, Huaming Wang, Zhenghao Wang, Jun Zhang, Yong Zhao, Tianyan Zhou

This increases marginally to 1. 6% when 50% of the attendees are unknown to the system.

speaker-diarization Speaker Diarization +2

Low-Latency Speaker-Independent Continuous Speech Separation

no code implementations • 13 Apr 2019 • Takuya Yoshioka, Zhuo Chen, Changliang Liu, Xiong Xiao, Hakan Erdogan, Dimitrios Dimitriadis

Speaker independent continuous speech separation (SI-CSS) is a task of converting a continuous audio stream, which may contain overlapping voices of unknown speakers, into a fixed number of continuous signals each of which contains no overlapping speech segment.

speech-recognition Speech Recognition +1

Layer Trajectory LSTM

no code implementations • 28 Aug 2018 • Jinyu Li, Changliang Liu, Yifan Gong

In this paper, we propose a layer trajectory LSTM (ltLSTM) which builds a layer-LSTM using all the layer outputs from a standard multi-layer time-LSTM.

Developing Far-Field Speaker System Via Teacher-Student Learning

no code implementations • 14 Apr 2018 • Jinyu Li, Rui Zhao, Zhuo Chen, Changliang Liu, Xiong Xiao, Guoli Ye, Yifan Gong

In this study, we develop the keyword spotting (KWS) and acoustic model (AM) components in a far-field speaker system.

Keyword Spotting Model Compression