Synthesis

Technology Pipeline for Large Scale Cross-Lingual Dubbing of Lecture Videos into Multiple Indian Languages Interspeech 2023 Text Only Domain Adaptation with Phoneme Guided Data Splicing for End-to-End Speech Recognition Interspeech 2023 The effect of masking noise on listeners’ spectral tilt preferences Interspeech 2023 The HW-TSC’s Speech-to-Speech Translation System for IWSLT 2023 ACL 2023 The Interpreter Understands Your Meaning: End-to-end Spoken Language Understanding Aided by Speech Translation EMNLP 2023 The Kyoto Speech-to-Speech Translation System for IWSLT 2023 ACL 2023 The MineTrans Systems for IWSLT 2023 Offline Speech Translation and Speech-to-Speech Translation Tasks ACL 2023 The NPU-MSXF Speech-to-Speech Translation System for IWSLT 2023 Speech-to-Speech Translation Task ACL 2023 The Role of Formant and Excitation Source Features in Perceived Naturalness of Low Resource Tribal Language TTS: An Empirical Study Interspeech 2023 Time-Domain Speech Enhancement for Robust Automatic Speech Recognition Interspeech 2023 Time-frequency Domain Filter-and-sum Network for Multi-channel Speech Separation Interspeech 2023 TokenSplit: Using Discrete Speech Representations for Direct, Refined, and Transcript-Conditioned Speech Separation and Recognition Interspeech 2023 Toward Joint Language Modeling for Speech Units and Text EMNLP 2023 Towards Fully Quantized Neural Networks For Speech Enhancement Interspeech 2023 Towards Real-World Streaming Speech Translation for Code-Switched Speech EMNLP 2023 Towards Robust FastSpeech 2 by Modelling Residual Multimodality Interspeech 2023 Towards Spontaneous Style Modeling with Semi-supervised Pre-training for Conversational Text-to-Speech Synthesis Interspeech 2023 Towards Two-point Neuron-inspired Energy-efficient Multimodal Open Master Hearing Aid Interspeech 2023 Towards Voice Reconstruction from EEG during Imagined Speech AAAI 2023 TridentSE: Guiding Speech Enhancement with 32 Global Tokens Interspeech 2023 Two-Stage Voice Anonymization for Enhanced Privacy Interspeech 2023 Ultra Dual-Path Compression For Joint Echo Cancellation And Noise Suppression Interspeech 2023 UniFLG: Unified Facial Landmark Generator from Text or Speech Interspeech 2023 UniSplice: Universal Cross-Lingual Data Splicing for Low-Resource ASR Interspeech 2023 UniSyn: An End-to-End Unified Model for Text-to-Speech and Singing Voice Synthesis AAAI 2023