Keeletehnoloogia seminar: kõnetehnoloogia 2021/22 kevad

Topics

A list of papers required for each seminar is provided below.

Please sign up for presenting 1 paper and leading the discussion on 2 papers here.

• February 11: no seminar
• February 18: Introduction to text-to-speech
  • No reading required
• February 25: no seminar
• March 4: text-to-speech
  • FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
  • Transformer-based Acoustic Modeling for Streaming Speech Synthesis
• March 11: Text-to-speech
  • Adaptive Text to Speech for Spontaneous Style
  • TacoSpawn: Speaker Generation
• March 18: Introduction to speech recognition
  • No reading required
• March 25: Automatic speech recognition
  • Conformer: Convolution-augmented Transformer for Speech Recognition
  • Developing Real-time Streaming Transformer Transducer for Speech Recognition on Large-scale Dataset
• April 1: Automatic speech recognition
  • Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition
  • Improved Noisy Student Training for Automatic Speech Recognition
• April 8: Introduction to advanced topics in speech processing (Speech modeling slides, Speech translation slides)
  • No reading required
• April 15: no seminar (Good Friday)
• April 22: Speech modeling
  • W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training
  • Text-Free Prosody-Aware Generative Spoken Language Modeling
• April 29: Speech translation
  • Direct speech-to-speech translation with discrete units
  • SpecRec: An Alternative Solution for Improving End-to-End Speech-to-Text Translation via Spectrogram Reconstruction
• May 6: Speech analysis
  • Speech Emotion Recognition with Multi-Task Learning
  • End-to-End Spoken Language Understanding for Generalized Voice Assistants