Skip to search formSkip to main contentSkip to account menu
Deep clustering: Discriminative embeddings for segmentation and separation
TLDR
Preliminary experiments on single-channel mixtures from multiple speakers show that a speaker-independent model trained on two-speaker mixtures can improve signal quality for mixtures of held-out speakers by an average of 6dB, and the same model does surprisingly well with three-speakers mixtures.
View on IEEE
ESPnet: End-to-End Speech Processing Toolkit
TLDR
A major architecture of this software platform, several important functionalities, which differentiate ESPnet from other open source ASR toolkits, and experimental results with major ASR benchmarks are explained.
View PDF on arXiv
The third ‘CHiME’ speech separation and recognition challenge: Dataset, task and baselines
TLDR
The design and outcomes of the 3rd CHiME Challenge, which targets the performance of automatic speech recognition in a real-world, commercially-motivated scenario: a person talking to a tablet device that has been fitted with a six-channel microphone array, are presented.
View on IEEE
Phase-sensitive and recognition-boosted speech separation using deep recurrent neural networks
TLDR
A phase-sensitive objective function based on the signal-to-noise ratio (SNR) of the reconstructed signal is developed, and it is shown that in experiments it yields uniformly better results in terms of signal- to-distortion ratio (SDR).
View on IEEE
Joint CTC-attention based end-to-end speech recognition using multi-task learning
TLDR
A novel method for end-to-end speech recognition to improve robustness and achieve fast convergence by using a joint CTC-attention model within the multi-task learning framework, thereby mitigating the alignment issue.
View on IEEE
Single-Channel Multi-Speaker Separation Using Deep Clustering
TLDR
This paper significantly improves upon the baseline system performance by incorporating better regularization, larger temporal context, and a deeper architecture, culminating in an overall improvement in signal to distortion ratio (SDR) of 10.3 dB compared to the baseline, and produces unprecedented performance on a challenging speech separation.
View PDF on arXiv
Hybrid CTC/Attention Architecture for End-to-End Speech Recognition
TLDR
The proposed hybrid CTC/attention end-to-end ASR is applied to two large-scale ASR benchmarks, and exhibits performance that is comparable to conventional DNN/HMM ASR systems based on the advantages of both multiobjective learning and joint decoding without linguistic resources.
View on IEEE
Speech Enhancement with LSTM Recurrent Neural Networks and its Application to Noise-Robust ASR
TLDR
It is demonstrated that LSTM speech enhancement, even when used 'naively' as front-end processing, delivers competitive results on the CHiME-2 speech recognition task.
View via Publisher
An analysis of environment, microphone and data simulation mismatches in robust speech recognition
View via Publisher
A Comparative Study on Transformer vs RNN in Speech Applications
TLDR
An emergent sequence-to-sequence model called Transformer achieves state-of-the-art performance in neural machine translation and other natural language processing applications, including the surprising superiority of Transformer in 13/15 ASR benchmarks in comparison with RNN.
View on IEEE
...
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy, Terms of Service, and Dataset License