paper-with-me

Papers

Continuous Speech Separation with Conformer

2020-08-13 · Sanyuan Chen, Yu Wu, Zhuo Chen, Jian Wu, Jinyu Li, Takuya Yoshioka, Chengyi Wang, Shujie Liu, Ming Zhou

Continuous speech separation plays a vital role in complicated speech related tasks such as conversation transcription. The separation model extracts a single speaker signal from a mixed speech. In this paper, we use transformer and conformer in lieu of recurrent neural networks in the separation system, as we believe capturing global information with the self-attention based method is crucial for the speech separation. Evaluating on the LibriCSS dataset, the conformer separation model achieves state of the art results, with a relative 23.5% word error rate (WER) reduction from bi-directional LSTM (BLSTM) in the utterance-wise evaluation and a 15.4% WER reduction in the continuous evaluation.

📄 PDF Abstract BibTeX arXiv:2008.05773

Code (1)

Sanyuan-Chen/CSS_with_Conformer pytorch

Tasks

Speech Separation

Methods 이 논문이 사용한 방법론

Tanh Activation 설명 없음
Sigmoid Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Similar Papers 제목 키워드 기반

On Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant Acoustic Environments

2023-10-09 · William Ravenscroft, Stefan Goetze, Thomas Hain

Speech separation remains an important topic for multi-speaker technology researchers. Convolution augmented transformers (conformers) have performed well for many speech processing tasks but have been under-researched f…

Computational EfficiencySpeech Separation

VarArray: Array-Geometry-Agnostic Continuous Speech Separation

2021-10-12 · Takuya Yoshioka, Xiaofei Wang, Dongmei Wang, Min Tang 외

Continuous speech separation using a microphone array was shown to be promising in dealing with the speech overlap problem in natural conversation transcription. This paper proposes VarArray, an array-geometry-agnostic s…

Speech Separation

Multi-Dimensional and Multi-Scale Modeling for Speech Separation Optimized by Discriminative Learning

2023-03-07 · Zhaoxi Mu, Xinyu Yang, Wenjing Zhu

Transformer has shown advanced performance in speech separation, benefiting from its ability to capture global features. However, capturing local features and channel information of audio sequences in speech separation i…

Speech Separation

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios

2025-06-17 · Aswin Shanmugam Subramanian, Amit Das, Naoyuki Kanda, Jinyu Li 외

We extend the frameworks of Serialized Output Training (SOT) to address practical needs of both streaming and offline automatic speech recognition (ASR) applications. Our approach focuses on balancing latency and accurac…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition+1

The RoyalFlush System of Speech Recognition for M2MeT Challenge

2022-02-03 · Shuaishuai Ye, Peiyao Wang, Shunfei Chen, Xinhui Hu 외

This paper describes our RoyalFlush system for the track of multi-speaker automatic speech recognition (ASR) in the M2MeT challenge. We adopted the serialized output training (SOT) based multi-speakers ASR system with la…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Data AugmentationDecoder+4