INTERSPEECH2020大会收录了哪些论文？

*转载文章请留言联系作者

众所周知，INTERSPEECH论文的入选门槛较高，竞争异常激烈，那今年有哪些论文被大会收录了呢？

我们根据语音的几个方向对顶会收录的153篇论文进行了整理汇总，希望可以帮助大家快速获取想要的论文~

整理的论文主要分为以下几个语音领域方向：

• 语音合成
• 语音识别
• 场景&说话人识别
• 语音增强
• 多模&翻译

 

1. 语音合成

1.A Cyclical Post-filtering Approach to Mismatch Refinement of Neural Vocoder for Text-to-speech Systems.pdf

2.Attentron Few-Shot Text-to-Speech Utilizing Attention-Based Variable-Length Embedding.pdf

3.Bunched LPCNet Vocoder for Low-cost Neural Text-To-Speech Systems.pdf

4.Can Speaker Augmentation Improve Multi-Speaker End-to-End TTS.pdf

5.Controllable Neural Prosody Synthesis.pdf

6.Converting Anyone’s Emotion Towards Speaker-Independent Emotional Voice Conversion.pdf

7.Deep MOS Predictor for Synthetic Speech Using Cluster-Based Modeling.pdf

8.DurIAN-SC Duration Informed Attention Network based Singing Voice Conversion System.pdf

9.Enhancing Speech Intelligibility in Text-To-Speech Synthesis using Speaking Style Conversion.pdf

10.Exploring TTS without T Using BiologicallyPsychologically Motivated Neural Network Modules (ZeroSpeech 2020).pdf

11.From Speaker Verification to Multispeaker Speech Synthesis, Deep Transfer with Feedback Constraint.pdf

12.Incremental Text to Speech for Neural Sequence-to-Sequence Models using Reinforcement Learning.pdf

13.Quasi-Periodic Parallel WaveGAN Vocoder A Non-autoregressive Pitchdependent Dilated Convolution Model for Parametric Speech Generation.pdf

14.Multi-speaker Text-to-speech Synthesis Using Deep Gaussian Processes.pdf

15.Neural Text-to-Speech with a Modeling-by-Generation Excitation Vocoder.pdf

16.One Model, Many Languages Meta-learning for Multilingual Text-to-Speech.pdf

17.Peking Opera Synthesis via Duration Informed Attention Network.pdf

18.Phonological Features for 0-shot Multilingual Speech Synthesis.pdf

19.Proc. Interspeech 2020-Improving Opus Low Bit Rate Quality with Neural Speech Synthesis.pdf

20.Prosody Learning Mechanism for Speech Synthesis System Without Text Length Limit.pdf

21.Quantification of Transducer Misalignment in Ultrasound Tongue Imaging.pdf

22.Recognition-Synthesis Based Non-Parallel Voice Conversion with Adversarial Learning.pdf

23.Semi-supervised Learning for Multi-speaker Text-to-speech Synthesis Using Discrete Speech Representation.pdf

24.Speaker Conditional WaveRNN Towards Universal Neural Vocoder for Unseen Speaker and Recording Conditions.pdf

25.Speaking Speed Control of End-to-End Speech Synthesis using Sentence-Level Conditioning.pdf

26.Speech-to-Singing Conversion based on Boundary Equilibrium GAN.pdf

27.SpeedySpeech Efficient Neural Speech Synthesis.pdf

28.Ultrasound-based Articulatory-to-Acoustic Mapping with WaveGlow Speech Synthesis-Ultrasound-based Articulatory-to-Acoustic Mapping with WaveGlow Speech Synthesis.pdf

29.Understanding Self-Attention of Self-Supervised Audio Transformers.pdf

30.Unsupervised Learning For Sequence-to-sequence Text-to-speech For Low-resource Languages.pdf

31.Utterance-Wise Meeting Transcription System Using Asynchronous Distributed Microphones.pdf

32.VocGAN A High-Fidelity Real-time Vocoder with a Hierarchically-nested Adversarial Network.pdf

33.Vocoder-Based Speech Synthesis from Silent Videos.pdf

34.WG-WaveNet Real-Time High-Fidelity Speech Synthesis without GPU.pdf

 

2. 语音识别

Interspeech 2020收录了大约61篇语音识别的论文，以下是部分论文题目。（论文集中是完整的61篇论文）

1.Augmenting Generative Adversarial Networks for Speech Emotion Recognition.pdf

2.Automatic Detection of Phonological Errors in Child Speech Using Siamese Recurrent Autoencoder.pdf

3.Autosegmental Neural Nets Should Phones and Tones be Synchronous or Asynchronous.pdf

4.CAT A CTC-CRF based ASR Toolkit Bridging the Hybrid and the End-to-end Approaches towards Data Efficiency and Low Latency.pdf

5.CLASS LM AND WORD MAPPING FOR CONTEXTUAL BIASING IN END-TO-END ASR.pdf

6.Conference paper at Interspeech 2020-Evaluating the reliability of acoustic speech embeddings.pdf

7.Conv-Transformer Transducer Low Latency, Low Frame Rate, Streamable End-to-End Speech Recognition.pdf

8.Cosine-Distance Virtual Adversarial Training for Semi-Supervised Speaker-Discriminative Acoustic Embeddings.pdf

9.Cotatron Transcription-Guided Speech Encoder for Any-to-Many Voice Conversion without Parallel Data.pdf

10.DARTS-ASR Differentiable Architecture Search for Multilingual Speech Recognition and Adaptation.pdf

 

3. 场景&说话人识别

Interspeech 2020收录了大约34篇场景&说话人识别的论文，以下是部分论文题目。（论文集中是完整的34篇论文）

1.End-to-End Speaker Diarization for an Unknown Number of Speakers with Encoder-Decoder Based Attractors.pdf

2.Evolutionary Algorithm Enhanced Neural Architecture Search for Text-Independent Speaker Verification.pdf

3.Exploring the Use of an Unsupervised Autoregressive Model as a Shared Encoder for Text-Dependent Speaker Verification.pdf

4.Extrapolating False Alarm Rates in Automatic Speaker Verification.pdf

5.Identify Speakers in Cocktail Parties with End-to-End Attention.pdf

6.Improving Multi-Scale Aggregation Using Feature Pyramid Module for Robust Speaker Verification of Variable-Duration Utterances.pdf

7.Improving on-device speaker verification using federated learning with privacy.pdf

8.Interspeech 2020-Sum-Product Networks for Robust Automatic Speaker Identification.pdf

9.JukeBox A Multilingual Singer Recognition Dataset.pdf

10.Length- and Noise-aware Training Techniques for Short-utterance Speaker Recognition.pdf

 

4.语音增强

Interspeech 2020收录了大约24篇场景&说话人识别的论文，以下是部分论文题目。（论文集中是完整的24篇论文）

1.Deep Noise Suppression Challenge Datasets, Subjective Testing Framework, and Challenge Results.pdf

2.Do face masks introduce bias in speech technologies The case of automated scoring of speaking proficiency.pdf

3.Dual-Path Transformer Network Direct Context-Aware Modeling for End-to-End Monaural Speech Separation.pdf

4.Efficient Low-Latency Speech Enhancement with Mobile Audio Streaming Networks.pdf

5.Exploring Deep Hybrid Tensor-to-Vector Network Architectures for Regression Based Speech Enhancement.pdf

6.g2pM A Neural Grapheme-to-Phoneme Conversion Package for Mandarin Chinese Based on a New Open Benchmark Dataset.pdf

 

4.翻译&多模

翻译的论文有1篇

Efficient Wait-k Models for Simultaneous Machine Translation.pdf

多模方向的论文有3篇

1.Automatic Quality Assessment for Audio-Visual Verification.pdf

Systems. The LOVe submission to NIST SRE Challenge 2019

2.End-to-End Lip Synchronisation.pdf

3.Unsupervised vs. transfer learning for multimodal one-shot matching of speech and images.pdf

我们已经帮小伙伴们准备好了153篇Interspeech 2020论文集，快来解读顶会的前沿研究与技术吧！

论文获取方式

添加叶子：shenlanyez，备注“语音论文”即可领取~

* 感谢深蓝学院多门语音课程的优秀学员——龙岩同学，在百忙之中协助我们细分了论文的各个领域方向！