Alert button
Picture for Yuzong Liu

Yuzong Liu

Alert button

On-Device Constrained Self-Supervised Speech Representation Learning for Keyword Spotting via Knowledge Distillation

Jul 06, 2023
Gene-Ping Yang, Yue Gu, Qingming Tang, Dongsu Du, Yuzong Liu

Figure 1 for On-Device Constrained Self-Supervised Speech Representation Learning for Keyword Spotting via Knowledge Distillation
Figure 2 for On-Device Constrained Self-Supervised Speech Representation Learning for Keyword Spotting via Knowledge Distillation
Figure 3 for On-Device Constrained Self-Supervised Speech Representation Learning for Keyword Spotting via Knowledge Distillation
Figure 4 for On-Device Constrained Self-Supervised Speech Representation Learning for Keyword Spotting via Knowledge Distillation
Viaarxiv icon

Small-footprint slimmable networks for keyword spotting

Apr 21, 2023
Zuhaib Akhtar, Mohammad Omar Khursheed, Dongsu Du, Yuzong Liu

Figure 1 for Small-footprint slimmable networks for keyword spotting
Figure 2 for Small-footprint slimmable networks for keyword spotting
Figure 3 for Small-footprint slimmable networks for keyword spotting
Figure 4 for Small-footprint slimmable networks for keyword spotting
Viaarxiv icon

Self-supervised speech representation learning for keyword-spotting with light-weight transformers

Mar 07, 2023
Chenyang Gao, Yue Gu, Francesco Caliva, Yuzong Liu

Figure 1 for Self-supervised speech representation learning for keyword-spotting with light-weight transformers
Figure 2 for Self-supervised speech representation learning for keyword-spotting with light-weight transformers
Figure 3 for Self-supervised speech representation learning for keyword-spotting with light-weight transformers
Figure 4 for Self-supervised speech representation learning for keyword-spotting with light-weight transformers
Viaarxiv icon

Fixed-point quantization aware training for on-device keyword-spotting

Mar 04, 2023
Sashank Macha, Om Oza, Alex Escott, Francesco Caliva, Robbie Armitano, Santosh Kumar Cheekatmalla, Sree Hari Krishnan Parthasarathi, Yuzong Liu

Figure 1 for Fixed-point quantization aware training for on-device keyword-spotting
Figure 2 for Fixed-point quantization aware training for on-device keyword-spotting
Figure 3 for Fixed-point quantization aware training for on-device keyword-spotting
Figure 4 for Fixed-point quantization aware training for on-device keyword-spotting
Viaarxiv icon

Sub 8-Bit Quantization of Streaming Keyword Spotting Models for Embedded Chipsets

Jul 13, 2022
Lu Zeng, Sree Hari Krishnan Parthasarathi, Yuzong Liu, Alex Escott, Santosh Cheekatmalla, Nikko Strom, Shiv Vitaladevuni

Figure 1 for Sub 8-Bit Quantization of Streaming Keyword Spotting Models for Embedded Chipsets
Figure 2 for Sub 8-Bit Quantization of Streaming Keyword Spotting Models for Embedded Chipsets
Figure 3 for Sub 8-Bit Quantization of Streaming Keyword Spotting Models for Embedded Chipsets
Figure 4 for Sub 8-Bit Quantization of Streaming Keyword Spotting Models for Embedded Chipsets
Viaarxiv icon

DeCoAR 2.0: Deep Contextualized Acoustic Representations with Vector Quantization

Dec 11, 2020
Shaoshi Ling, Yuzong Liu

Figure 1 for DeCoAR 2.0: Deep Contextualized Acoustic Representations with Vector Quantization
Figure 2 for DeCoAR 2.0: Deep Contextualized Acoustic Representations with Vector Quantization
Figure 3 for DeCoAR 2.0: Deep Contextualized Acoustic Representations with Vector Quantization
Figure 4 for DeCoAR 2.0: Deep Contextualized Acoustic Representations with Vector Quantization
Viaarxiv icon

Transformer-Transducers for Code-Switched Speech Recognition

Nov 30, 2020
Siddharth Dalmia, Yuzong Liu, Srikanth Ronanki, Katrin Kirchhoff

Figure 1 for Transformer-Transducers for Code-Switched Speech Recognition
Figure 2 for Transformer-Transducers for Code-Switched Speech Recognition
Figure 3 for Transformer-Transducers for Code-Switched Speech Recognition
Figure 4 for Transformer-Transducers for Code-Switched Speech Recognition
Viaarxiv icon

Streaming Language Identification using Combination of Acoustic Representations and ASR Hypotheses

Jun 01, 2020
Chander Chandak, Zeynab Raeesy, Ariya Rastrow, Yuzong Liu, Xiangyang Huang, Siyu Wang, Dong Kwon Joo, Roland Maas

Figure 1 for Streaming Language Identification using Combination of Acoustic Representations and ASR Hypotheses
Figure 2 for Streaming Language Identification using Combination of Acoustic Representations and ASR Hypotheses
Figure 3 for Streaming Language Identification using Combination of Acoustic Representations and ASR Hypotheses
Figure 4 for Streaming Language Identification using Combination of Acoustic Representations and ASR Hypotheses
Viaarxiv icon

Deep Contextualized Acoustic Representations For Semi-Supervised Speech Recognition

Dec 03, 2019
Shaoshi Ling, Yuzong Liu, Julian Salazar, Katrin Kirchhoff

Figure 1 for Deep Contextualized Acoustic Representations For Semi-Supervised Speech Recognition
Figure 2 for Deep Contextualized Acoustic Representations For Semi-Supervised Speech Recognition
Figure 3 for Deep Contextualized Acoustic Representations For Semi-Supervised Speech Recognition
Figure 4 for Deep Contextualized Acoustic Representations For Semi-Supervised Speech Recognition
Viaarxiv icon

End-to-end Anchored Speech Recognition

Feb 06, 2019
Yiming Wang, Xing Fan, I-Fan Chen, Yuzong Liu, Tongfei Chen, Björn Hoffmeister

Figure 1 for End-to-end Anchored Speech Recognition
Figure 2 for End-to-end Anchored Speech Recognition
Figure 3 for End-to-end Anchored Speech Recognition
Figure 4 for End-to-end Anchored Speech Recognition
Viaarxiv icon