116 citations · 808 across the 43 of their papers we have counts for
11 papers · 1 filter
Advances in Online Audio-Visual Meeting Transcription
Takuya Yoshioka, Igor Abramovski, Cem Aksoylar +23
This paper describes a system that generates speaker-annotated transcripts of meetings by using a microphone array and a 360-degree camera. The hallmark of the system is its abilit…
Speaker Adaptation for Attention-Based End-to-End Speech Recognition
Zhong Meng, Yashesh Gaur, Jinyu Li +1
We propose three regularization-based speaker adaptation approaches to adapt the attention-based encoder-decoder (AED) model with very limited adaptation data from target speakers…
Improving RNN Transducer Modeling for End-to-End Speech Recognition
Jinyu Li, Rui Zhao, Hu Hu +1
In the last few years, an emerging trend in automatic speech recognition research is the study of end-to-end (E2E) systems. Connectionist Temporal Classification (CTC), Attention E…
Self-Teaching Networks
Liang Lu, Eric Sun, Yifan Gong
We propose self-teaching networks to improve the generalization capacity of deep neural networks. The idea is to generate soft supervision labels using the output layer for trainin…
PyKaldi2: Yet another speech toolkit based on Kaldi and PyTorch
Liang Lu, Xiong Xiao, Zhuo Chen +1
We introduce PyKaldi2 speech recognition toolkit implemented based on Kaldi and PyTorch. While similar toolkits are available built on top of the two, a key feature of PyKaldi2 is…
Encrypted Speech Recognition using Deep Polynomial Networks
Shi-Xiong Zhang, Yifan Gong, Dong Yu
The cloud-based speech recognition/API provides developers or enterprises an easy way to create speech-enabled features in their applications. However, sending audios about persona…
Adversarial Speaker Adaptation
Zhong Meng, Jinyu Li, Yifan Gong
We propose a novel adversarial speaker adaptation (ASA) scheme, in which adversarial learning is applied to regularize the distribution of deep hidden features in a speaker-depende…
Adversarial Speaker Verification
Zhong Meng, Yong Zhao, Jinyu Li +1
The use of deep networks to extract embeddings for speaker recognition has proven successfully. However, such embeddings are susceptible to performance degradation due to the misma…
Attentive Adversarial Learning for Domain-Invariant Training
Zhong Meng, Jinyu Li, Yifan Gong
Adversarial domain-invariant training (ADIT) proves to be effective in suppressing the effects of domain variability in acoustic modeling and has led to improved performance in aut…
Conditional Teacher-Student Learning
Zhong Meng, Jinyu Li, Yong Zhao +1
The teacher-student (T/S) learning has been shown to be effective for a variety of problems such as domain adaptation and model compression. One shortcoming of the T/S learning is…
Speaker Adaptation for End-to-End CTC Models
Ke Li, Jinyu Li, Yong Zhao +2
We propose two approaches for speaker adaptation in end-to-end (E2E) automatic speech recognition systems. One is Kullback-Leibler divergence (KLD) regularization and the other is…