Search Results for author:
Found 23 papers, 2 papers with code
Spike-Triggered Non-Autoregressive Transformer for End-to-End Speech Recognition
To address this problem and improve the inference speed, we propose a spike-triggered non-autoregressive transformer model for end-to-end speech recognition, which introduces a CTC module to predict the length of the target sequence and accelerate the convergence.
Listen Attentively, and Spell Once: Whole Sentence Generation via a Non-Autoregressive Architecture for Low-Latency Speech Recognition
Without beam-search, the one-pass propagation much reduces inference time cost of LASO.
Simultaneous Denoising and Dereverberation Using Deep Embedding Features
In this paper, we propose a joint training method for simultaneous speech denoising and dereverberation using deep embedding features, which is based on the deep clustering (DC).
Adversarial Transfer Learning for Punctuation Restoration
The other is that POS tags are provided by an external POS tagger.
Deep Attention Fusion Feature for Speech Separation with End-to-End Post-filter Method
Secondly, to pay more attention to the outputs of the pre-separation stage, an attention module is applied to acquire deep attention fusion features, which are extracted by computing the similarity between the mixture and the pre-separated speech.
Rnn-transducer with language bias for end-to-end Mandarin-English code-switching speech recognition
Recently, language identity information has been utilized to improve the performance of end-to-end code-switching (CS) speech recognition.
Spatial and spectral deep attention fusion for multi-channel speech separation using deep embedding features
Specifically, we apply the deep clustering network to extract deep embedding features.
Synchronous Transformers for End-to-End Speech Recognition
Once a fixed-length chunk of the input sequence is processed by the encoder, the decoder begins to predict symbols immediately.
Integrating Knowledge into End-to-End Speech Recognition from External Text-Only Data
To alleviate the above two issues, we propose a unified method called LST (Learn Spelling from Teachers) to integrate knowledge into an AED model from the external text-only data and leverage the whole context in a sentence.
Unsupervised Representation Learning with Future Observation Prediction for Speech Emotion Recognition
Prior works on speech emotion recognition utilize various unsupervised learning approaches to deal with low-resource samples.
Conversational Emotion Analysis via Attention Mechanisms
Different from the emotion recognition in individual utterances, we propose a multimodal learning framework using relation and dependencies among the utterances for conversational emotion analysis.
Domain adversarial learning for emotion recognition
The secondary task is to learn a common representation where speaker identities can not be distinguished.
Expression Analysis Based on Face Regions in Read-world Conditions
To sum up, the contributions of this paper lie in two areas: 1) We visualize concerned areas of human faces in emotion recognition; 2) We analyze the contribution of different face areas to different emotions in real-world conditions through experimental analysis.
Speech Emotion Recognition via Contrastive Loss under Siamese Networks
It outperforms the baseline system that is optimized without the contrastive loss function with 1. 14% and 2. 55% in the weighted accuracy and the unweighted accuracy, respectively.
Self-Attention Transducers for End-to-End Speech Recognition
Furthermore, a path-aware regularization is proposed to assist SA-T to learn alignments and improve the performance.
Discriminative Learning for Monaural Speech Separation Using Deep Embedding Features
Firstly, a DC network is trained to extract deep embedding features, which contain each source's information and have an advantage in discriminating each target speakers.
Forward-Backward Decoding for Regularizing End-to-End TTS
Experimental results show our proposed methods especially the second one (bidirectional decoder regularization), leads a significantly improvement on both robustness and overall naturalness, as outperforming baseline (the revised version of Tacotron2) with a MOS gap of 0. 14 in a challenging test, and achieving close to human quality (4. 42 vs. 4. 49 in MOS) on general test.
Learn Spelling from Teachers: Transferring Knowledge from Language Models to Sequence-to-Sequence Speech Recognition
Integrating an external language model into a sequence-to-sequence speech recognition system is non-trivial.
Reinforcement Learning Based Emotional Editing Constraint Conversation Generation
In recent years, the generation of conversation content based on deep neural networks has attracted many researchers.
Improving speech emotion recognition via Transformer-based Predictive Coding through transfer learning
I have submitted a new version to arXiv:1910. 13806.
Investigation of Multimodal Features, Classifiers and Fusion Methods for Emotion Recognition
We test our method in the EmotiW 2018 challenge and we gain promising results.
Distilling Knowledge Using Parallel Data for Far-field Speech Recognition
The close-talking model is called the teacher model.
Audio Visual Emotion Recognition with Temporal Alignment and Perception Attention
The other one is locating and re-weighting the perception attentions in the whole audio-visual stream for better recognition.
