Speech & Audio

KIT’s IWSLT 2021 Offline Speech Translation System ACL 2021 Knowledge Distillation Based Training of Universal ASR Source Models for Cross-Lingual Transfer Interspeech 2021 Know Your Enemy, Know Yourself: A Unified Two-Stage Framework for Speech Enhancement Interspeech 2021 kosp2e: Korean Speech to English Translation Corpus Interspeech 2021 LACOPE: Latency-Constrained Pitch Estimation for Speech Enhancement Interspeech 2021 Lalilo: A Reading Assistant for Children Featuring Speech Recognition-Based Reading Mistake Detection Interspeech 2021 Language and Speaker-Independent Feature Transformation for End-to-End Multilingual Speech Recognition Interspeech 2021 Language ID Prediction from Speech Using Self-Attentive Pooling NAACL 2021 Language Recognition Based on Unsupervised Pretrained Models Interspeech 2021 Large-Scale Pre-Training of End-to-End Multi-Talker ASR for Meeting Transcription with Single Distant Microphone Interspeech 2021 Large-Scale Self- and Semi-Supervised Learning for Speech Translation Interspeech 2021 Late Fusion of the Available Lexicon and Raw Waveform-Based Acoustic Modeling for Depression and Dementia Recognition Interspeech 2021 Layer Pruning on Demand with Intermediate CTC Interspeech 2021 Layer-Wise Fast Adaptation for End-to-End Multi-Accent Speech Recognition Interspeech 2021 Learning a Neural Diff for Speech Models Interspeech 2021 Learning Explicit Prosody Models and Deep Speaker Embeddings for Atypical Voice Conversion Interspeech 2021 Learning From the Master: Distilling Cross-Modal Advanced Knowledge for Lip Reading CVPR 2021 Learning Mutual Correlation in Multimodal Transformer for Speech Emotion Recognition Interspeech 2021 Learning Speech Structure to Improve Time-Frequency Masks Interspeech 2021 Learning to Rank Microphones for Distant Speech Recognition Interspeech 2021 LeBenchmark: A Reproducible Framework for Assessing Self-Supervised Representation Learning from Speech Interspeech 2021 Leveraging ASR N-Best in Deep Entity Retrieval Interspeech 2021 Leveraging End-to-End ASR for Endangered Language Documentation: An Empirical Study on Yolóxochitl Mixtec EACL 2021 Leveraging Non-Target Language Resources to Improve ASR Performance in a Target Language Interspeech 2021 Leveraging Phone Mask Training for Phonetic-Reduction-Robust E2E Uyghur Speech Recognition Interspeech 2021