Icassp 2020 Towards Unsupervised Speech

Media Summary: Alexander H. Liu, Tao Tu, Hung-yi Lee, Lin-shan Lee, ' Andy T. Liu, Shu-wen Yang, Po-Han Chi, Po-chun Hsu, Hung-yi Lee, 'MOCKINGJAY: MERL's Petros Boufounos is presenting a talk on "The Computational Sensing Revolution in Array Processing" for the industry ...

Icassp 2020 Towards Unsupervised Speech - Detailed Analysis & Overview

Alexander H. Liu, Tao Tu, Hung-yi Lee, Lin-shan Lee, ' Andy T. Liu, Shu-wen Yang, Po-Han Chi, Po-chun Hsu, Hung-yi Lee, 'MOCKINGJAY: MERL's Petros Boufounos is presenting a talk on "The Computational Sensing Revolution in Array Processing" for the industry ... Matthew Maciejewski presents his paper titled "WHAMR!: Noisy and Reverberant Single-Channel From PROmotinG diveRsity in signal procESSing (PROGRESS), held in conjunction with the 2022 IEEE International Conference ... Chung-Yi Li, Pei-Chieh Yuan, Hung-Yi Lee, 'WHAT DOES A NETWORK LAYER HEAR? ANALYZING HIDDEN ...

Da-Yi Wu, Hung-yi Lee, 'ONE-SHOT VOICE CONVERSION BY VECTOR QUANTIZATION', Gene-Ping Yang, Szu-Lin Wu, Yao-Wen Mao, Hung-yi Lee, Lin-shan Lee, 'INTERRUPTED AND CASCADED PERMUTATION ... Conference presentation outlining the results found in: V. Ardulov, Z. Durante, S. Williams, T. Lyon and S. Narayanan, "Identifying ...

Photo Gallery

[ICASSP 2020] TOWARDS UNSUPERVISED SPEECH RECOGNITION AND SYNTHESIS (Speaker: Tao Tu)

[ICASSP 2020] MOCKINGJAY: UNSUPERVISED SPEECH REPRESENTATION LEARNING (Speaker: Andy T. Liu)

[ICASSP 2020]Unsupervised Speaker Adaptation Using Attention-Based Speaker Memory for End-To-End ASR

[ICASSP 2020] The Computational Sensing Revolution in Array Processing

ICASSP 2020 - Lightweight and Efficient End-to-End Speech Recognition Using Low-Rank Transformer

[ICASSP 2020] WHAMR!: Noisy and Reverberant Single-Channel Speech Separation

ICASSP 2022: Opening Speech by SPS President Athina Petropulu

[ICASSP 2020] WHAT DOES A NETWORK LAYER HEAR? (Speaker: Chung-Yi Li)

[ICASSP 2020] ONE-SHOT VOICE CONVERSION BY VECTOR QUANTIZATION (Speaker: Da-Yi Wu)

[ICASSP 2020] INTERRUPTED AND CASCADED PIT FOR SPEECH SEPARATION (Speaker: Gene-Ping Yang)

[ICASSP 2020] BLASTER: An off-grid method for blind and regularized acoustic echoes retrieval

Toward Unsupervised Learning of Speech Representations

View Detailed Profile

[ICASSP 2020] TOWARDS UNSUPERVISED SPEECH RECOGNITION AND SYNTHESIS (Speaker: Tao Tu)

[ICASSP 2020] TOWARDS UNSUPERVISED SPEECH RECOGNITION AND SYNTHESIS (Speaker: Tao Tu)

Alexander H. Liu, Tao Tu, Hung-yi Lee, Lin-shan Lee, '

[ICASSP 2020] MOCKINGJAY: UNSUPERVISED SPEECH REPRESENTATION LEARNING (Speaker: Andy T. Liu)

[ICASSP 2020] MOCKINGJAY: UNSUPERVISED SPEECH REPRESENTATION LEARNING (Speaker: Andy T. Liu)

Andy T. Liu, Shu-wen Yang, Po-Han Chi, Po-chun Hsu, Hung-yi Lee, 'MOCKINGJAY:

[ICASSP 2020]Unsupervised Speaker Adaptation Using Attention-Based Speaker Memory for End-To-End ASR

[ICASSP 2020]Unsupervised Speaker Adaptation Using Attention-Based Speaker Memory for End-To-End ASR

Leda Sarı presents her paper titled "

[ICASSP 2020] The Computational Sensing Revolution in Array Processing

[ICASSP 2020] The Computational Sensing Revolution in Array Processing

MERL's Petros Boufounos is presenting a talk on "The Computational Sensing Revolution in Array Processing" for the industry ...

ICASSP 2020 - Lightweight and Efficient End-to-End Speech Recognition Using Low-Rank Transformer

ICASSP 2020 - Lightweight and Efficient End-to-End Speech Recognition Using Low-Rank Transformer

Oral presentation for

[ICASSP 2020] WHAMR!: Noisy and Reverberant Single-Channel Speech Separation

[ICASSP 2020] WHAMR!: Noisy and Reverberant Single-Channel Speech Separation

Matthew Maciejewski presents his paper titled "WHAMR!: Noisy and Reverberant Single-Channel

ICASSP 2022: Opening Speech by SPS President Athina Petropulu

ICASSP 2022: Opening Speech by SPS President Athina Petropulu

From PROmotinG diveRsity in signal procESSing (PROGRESS), held in conjunction with the 2022 IEEE International Conference ...

[ICASSP 2020] WHAT DOES A NETWORK LAYER HEAR? (Speaker: Chung-Yi Li)

[ICASSP 2020] WHAT DOES A NETWORK LAYER HEAR? (Speaker: Chung-Yi Li)

Chung-Yi Li, Pei-Chieh Yuan, Hung-Yi Lee, 'WHAT DOES A NETWORK LAYER HEAR? ANALYZING HIDDEN ...

[ICASSP 2020] ONE-SHOT VOICE CONVERSION BY VECTOR QUANTIZATION (Speaker: Da-Yi Wu)

[ICASSP 2020] ONE-SHOT VOICE CONVERSION BY VECTOR QUANTIZATION (Speaker: Da-Yi Wu)

Da-Yi Wu, Hung-yi Lee, 'ONE-SHOT VOICE CONVERSION BY VECTOR QUANTIZATION',

[ICASSP 2020] INTERRUPTED AND CASCADED PIT FOR SPEECH SEPARATION (Speaker: Gene-Ping Yang)

[ICASSP 2020] INTERRUPTED AND CASCADED PIT FOR SPEECH SEPARATION (Speaker: Gene-Ping Yang)

Gene-Ping Yang, Szu-Lin Wu, Yao-Wen Mao, Hung-yi Lee, Lin-shan Lee, 'INTERRUPTED AND CASCADED PERMUTATION ...

[ICASSP 2020] BLASTER: An off-grid method for blind and regularized acoustic echoes retrieval

[ICASSP 2020] BLASTER: An off-grid method for blind and regularized acoustic echoes retrieval

Video of our submission at

Toward Unsupervised Learning of Speech Representations

Toward Unsupervised Learning of Speech Representations

In this presentation, I first introduce

Identifying Truthful Language in Child Interviews - ICASSP 2020

Identifying Truthful Language in Child Interviews - ICASSP 2020

Conference presentation outlining the results found in: V. Ardulov, Z. Durante, S. Williams, T. Lyon and S. Narayanan, "Identifying ...