Speech & Audio

The Zero Resource Speech Challenge 2021: Spoken Language Modelling Interspeech 2021 Three-Module Modeling For End-to-End Spoken Language Understanding Using Pre-Trained DNN-HMM-Based Acoustic-Phonetic Model Interspeech 2021 Time Delay Estimation for Speaker Localization Using CNN-Based Parametrized GCC-PHAT Features Interspeech 2021 Token-Level Supervised Contrastive Learning for Punctuation Restoration Interspeech 2021 Towards an Accent-Robust Approach for ATC Communications Transcription Interspeech 2021 Towards Automatic Speech Recognition for People with Atypical Speech Interspeech 2021 Towards Lifelong Learning of End-to-End ASR Interspeech 2021 Towards Multi-Scale Style Control for Expressive Speech Synthesis Interspeech 2021 Towards One Model to Rule All: Multilingual Strategy for Dialectal Code-Switching Arabic ASR Interspeech 2021 Towards Simultaneous Machine Interpretation Interspeech 2021 Towards the Addition of Pronunciation Information to Lexical Semantic Resources EACL 2021 Towards the evaluation of automatic simultaneous speech translation from a communicative perspective ACL 2021 Towards the Explainability of Multimodal Speech Emotion Recognition Interspeech 2021 Toward Streaming ASR with Non-Autoregressive Insertion-Based Model Interspeech 2021 Towards Unsupervised Phone and Word Segmentation Using Self-Supervised Vector-Quantized Neural Networks Interspeech 2021 Training Hybrid Models on Noisy Transliterated Transcripts for Code-Switched Speech Recognition Interspeech 2021 Transcribing Paralinguistic Acoustic Cues to Target Language Text in Transformer-Based Speech-to-Text Translation Interspeech 2021 Transformer-Based Acoustic Modeling for Streaming Speech Synthesis Interspeech 2021 Transformer-Based ASR Incorporating Time-Reduction Layer and Fine-Tuning with Self-Knowledge Distillation Interspeech 2021 Triple M: A Practical Text-to-Speech Synthesis System with Multi-Guidance Attention and Multi-Band Multi-Time LPCNet Interspeech 2021 Tune-In: Training Under Negative Environments with Interference for Attention Networks Simulating Cocktail Party Effect AAAI 2021 Tusom2021: A Phonetically Transcribed Speech Dataset from an Endangered Language for Universal Phone Recognition Experiments Interspeech 2021 TVQVC: Transformer Based Vector Quantized Variational Autoencoder with CTC Loss for Voice Conversion Interspeech 2021 Two-Pathway Style Embedding for Arbitrary Voice Conversion Interspeech 2021 Uncovering the Acoustic Cues of COVID-19 Infection Interspeech 2021