苹果近日介绍了他们在 Interspeech 2019 的录取论文。分别是1. Leveraging Acoustic Cues and Paralinguistic Embeddings to Detect Expression from Voice 2. Bandwidth Embeddings for Mixed-bandwidth Speech Recognition 3. Neural Network-Based Modeling of Phonetic Durations 4. Connecting and Comparing Language Model Interpolation Techniques 5. Active Learning for Domain Classification in a Commercial Spoken Personal Assistant 6. Mirroring to Build Trust in Digital Assistants 7. Coarse-to-fine Optimization for Speech Enhancement