Should We Always Separate?: Switching Between Enhanced and Observed Signals for Overlapping Speech Recognition

2 June 2021

Papers citing "Should We Always Separate?: Switching Between Enhanced and Observed Signals for Overlapping Speech Recognition"

7 / 7 papers shown

Title
Rethinking Processing Distortions: Disentangling the Impact of Speech Enhancement Errors on Speech Recognition Performance Tsubasa Ochiai Kazuma Iwamoto Marc Delcroix Rintaro Ikeshita Hiroshi Sato Shoko Araki Shigeru Katagiri 29 2 0 23 Apr 2024
PP-MeT: a Real-world Personalized Prompt based Meeting Transcription System Xiang Lyu Yuhang Cao Qing Wang Jingjing Yin Yuguang Yang Pengpeng Zou G. Zachmann Heng Lu VLM 37 3 0 28 Sep 2023
Streaming Target-Speaker ASR with Neural Transducer Takafumi Moriya Hiroshi Sato Tsubasa Ochiai Marc Delcroix T. Shinozaki 31 21 0 09 Sep 2022
Speaker Reinforcement Using Target Source Extraction for Robust Automatic Speech Recognition Catalin Zorila R. Doddipatla 24 11 0 09 May 2022
Mask scalar prediction for improving robust automatic speech recognition A. Narayanan James Walker S. Panchapagesan N. Howard Yuma Koizumi 19 4 0 26 Apr 2022
One model to enhance them all: array geometry agnostic multi-channel personalized speech enhancement H. Taherian Sefik Emre Eskimez Takuya Yoshioka Huaming Wang Zhuo Chen Xuedong Huang 30 21 0 20 Oct 2021
Personalized Speech Enhancement: New Models and Comprehensive Evaluation Sefik Emre Eskimez Takuya Yoshioka Huaming Wang Xiaofei Wang Zhuo Chen Xuedong Huang 32 62 0 18 Oct 2021